SherbyNet - /page/wikibook/entry.mu

Micron Document

<!DOCTYPE html>

<title>TensorFlow</title>

</head>

<span id="openzim-page-title" class="mw-page-title-main"><span class="mw-page-title-main">TensorFlow</span></span>

</h1>

</header>

</p>

/* start https://en.wikipedia.org/ */

.mw-parser-output .infobox-subbox{padding:0;border:none;margin:-3px;width:auto;min-width:100%;font-size:100%;clear:none;float:none;background-color:transparent}.mw-parser-output .infobox-3cols-child{margin:auto}.mw-parser-output .infobox .navbar{font-size:100%}@media screen{html.skin-theme-clientpref-night .mw-parser-output .infobox-full-data:not(.notheme)>div:not(.notheme)[style]{background:#1f1f23!important;color:#f8f9fa}}@media screen and (prefers-color-scheme:dark){html.skin-theme-clientpref-os .mw-parser-output .infobox-full-data:not(.notheme)>div:not(.notheme)[style]{background:#1f1f23!important;color:#f8f9fa}}@media(min-width:640px){body.skin--responsive .mw-parser-output .infobox-table{display:table!important}body.skin--responsive .mw-parser-output .infobox-table>caption{display:table-caption!important}body.skin--responsive .mw-parser-output .infobox-table>tbody{display:table-row-group}body.skin--responsive .mw-parser-output .infobox-table th,body.skin--responsive .mw-parser-output .infobox-table td{padding-left:inherit;padding-right:inherit}}

/* end https://en.wikipedia.org/ */

</style><table class="infobox vevent"><tbody><tr><th colspan="2" class="infobox-above summary">TensorFlow</th></tr><tr><td colspan="2" class="infobox-image logo"><div class="infobox-caption">TensorFlow logo</div></td></tr><tr><th scope="row" class="infobox-label" style="white-space: nowrap;"><a href="Programmer" title="Programmer">Developer(s)</a></th><td class="infobox-data"><a href="Google_Brain" title="Google Brain">Google Brain</a> Team<sup id="cite_ref-Credits_1-0" class="reference"><a href="#cite_note-Credits-1"><span class="cite-bracket">[</span>1<span class="cite-bracket">]</span></a></sup></td></tr><tr><th scope="row" class="infobox-label" style="white-space: nowrap;">Initial release</th><td class="infobox-data">November 9, 2015<span style="display:none"> (<span class="bday dtstart published updated">2015-11-09</span>)</span></td></tr><tr style="display: none;"><td colspan="2" class="infobox-full-data"></td></tr><tr><th scope="row" class="infobox-label" style="white-space: nowrap;"><a href="Software_release_life_cycle" title="Software release life cycle">Stable release</a></th><td class="infobox-data"><div style="margin:0px;">2.19.0

/ March 11, 2025<span style="display:none"> (<span class="bday dtstart published updated">2025-03-11</span>)</span></div></td></tr><tr style="display:none"><td colspan="2">

</td></tr><tr><th scope="row" class="infobox-label" style="white-space: nowrap;"><a href="Repository_(version_control)" title="Repository (version control)">Repository</a></th><td class="infobox-data"><span class="url"><a rel="nofollow" class="external text" href="https://github.com/tensorflow/tensorflow">github<wbr>.com<wbr>/tensorflow<wbr>/tensorflow</a></span></td></tr><tr><th scope="row" class="infobox-label" style="white-space: nowrap;">Written in</th><td class="infobox-data"><a href="Python_(programming_language)" title="Python (programming language)">Python</a>, <a href="C%2B%2B" title="C++">C++</a>, <a href="CUDA" title="CUDA">CUDA</a></td></tr><tr><th scope="row" class="infobox-label" style="white-space: nowrap;"><a href="Computing_platform" title="Computing platform">Platform</a></th><td class="infobox-data"><a href="Linux" title="Linux">Linux</a>, <a href="MacOS" title="MacOS">macOS</a>, <a href="Windows" class="mw-redirect" title="Windows">Windows</a>, <a href="Android_(operating_system)" title="Android (operating system)">Android</a>, <a href="JavaScript" title="JavaScript">JavaScript</a><sup id="cite_ref-js_2-0" class="reference"><a href="#cite_note-js-2"><span class="cite-bracket">[</span>2<span class="cite-bracket">]</span></a></sup></td></tr><tr><th scope="row" class="infobox-label" style="white-space: nowrap;"><a href="Software_categories#Categorization_approaches" title="Software categories">Type</a></th><td class="infobox-data"><a href="Machine_learning" title="Machine learning">Machine learning</a> <a href="Library_(computing)" title="Library (computing)">library</a></td></tr><tr><th scope="row" class="infobox-label" style="white-space: nowrap;"><a href="Software_license" title="Software license">License</a></th><td class="infobox-data"><a href="Apache_License_2.0" class="mw-redirect" title="Apache License 2.0">Apache 2.0</a></td></tr><tr><th scope="row" class="infobox-label" style="white-space: nowrap;">Website</th><td class="infobox-data"><span class="url"><a rel="nofollow" class="external text" href="http://tensorflow.org">tensorflow<wbr>.org</a></span></td></tr></tbody></table>

/* start https://en.wikipedia.org/ */

.mw-parser-output .hlist dl,.mw-parser-output .hlist ol,.mw-parser-output .hlist ul{margin:0;padding:0}.mw-parser-output .hlist dd,.mw-parser-output .hlist dt,.mw-parser-output .hlist li{margin:0;display:inline}.mw-parser-output .hlist.inline,.mw-parser-output .hlist.inline dl,.mw-parser-output .hlist.inline ol,.mw-parser-output .hlist.inline ul,.mw-parser-output .hlist dl dl,.mw-parser-output .hlist dl ol,.mw-parser-output .hlist dl ul,.mw-parser-output .hlist ol dl,.mw-parser-output .hlist ol ol,.mw-parser-output .hlist ol ul,.mw-parser-output .hlist ul dl,.mw-parser-output .hlist ul ol,.mw-parser-output .hlist ul ul{display:inline}.mw-parser-output .hlist .mw-empty-li{display:none}.mw-parser-output .hlist dt::after{content:": "}.mw-parser-output .hlist dd::after,.mw-parser-output .hlist li::after{content:" · ";font-weight:bold}.mw-parser-output .hlist dd:last-child::after,.mw-parser-output .hlist dt:last-child::after,.mw-parser-output .hlist li:last-child::after{content:none}.mw-parser-output .hlist dd dd:first-child::before,.mw-parser-output .hlist dd dt:first-child::before,.mw-parser-output .hlist dd li:first-child::before,.mw-parser-output .hlist dt dd:first-child::before,.mw-parser-output .hlist dt dt:first-child::before,.mw-parser-output .hlist dt li:first-child::before,.mw-parser-output .hlist li dd:first-child::before,.mw-parser-output .hlist li dt:first-child::before,.mw-parser-output .hlist li li:first-child::before{content:" (";font-weight:normal}.mw-parser-output .hlist dd dd:last-child::after,.mw-parser-output .hlist dd dt:last-child::after,.mw-parser-output .hlist dd li:last-child::after,.mw-parser-output .hlist dt dd:last-child::after,.mw-parser-output .hlist dt dt:last-child::after,.mw-parser-output .hlist dt li:last-child::after,.mw-parser-output .hlist li dd:last-child::after,.mw-parser-output .hlist li dt:last-child::after,.mw-parser-output .hlist li li:last-child::after{content:")";font-weight:normal}.mw-parser-output .hlist ol{counter-reset:listitem}.mw-parser-output .hlist ol>li{counter-increment:listitem}.mw-parser-output .hlist ol>li::before{content:" "counter(listitem)"\a0 "}.mw-parser-output .hlist dd ol>li:first-child::before,.mw-parser-output .hlist dt ol>li:first-child::before,.mw-parser-output .hlist li ol>li:first-child::before{content:" ("counter(listitem)"\a0 "}

/* end https://en.wikipedia.org/ */

</style><style data-mw-deduplicate="TemplateStyles:r1246091330">

/* start https://en.wikipedia.org/ */

.mw-parser-output .sidebar{width:22em;float:right;clear:right;margin:0.5em 0 1em 1em;background:var(--background-color-neutral-subtle,#f8f9fa);border:1px solid var(--border-color-base,#a2a9b1);padding:0.2em;text-align:center;line-height:1.4em;font-size:88%;border-collapse:collapse;display:table}body.skin-minerva .mw-parser-output .sidebar{display:table!important;float:right!important;margin:0.5em 0 1em 1em!important}.mw-parser-output .sidebar-subgroup{width:100%;margin:0;border-spacing:0}.mw-parser-output .sidebar-left{float:left;clear:left;margin:0.5em 1em 1em 0}.mw-parser-output .sidebar-none{float:none;clear:both;margin:0.5em 1em 1em 0}.mw-parser-output .sidebar-outer-title{padding:0 0.4em 0.2em;font-size:125%;line-height:1.2em;font-weight:bold}.mw-parser-output .sidebar-top-image{padding:0.4em}.mw-parser-output .sidebar-top-caption,.mw-parser-output .sidebar-pretitle-with-top-image,.mw-parser-output .sidebar-caption{padding:0.2em 0.4em 0;line-height:1.2em}.mw-parser-output .sidebar-pretitle{padding:0.4em 0.4em 0;line-height:1.2em}.mw-parser-output .sidebar-title,.mw-parser-output .sidebar-title-with-pretitle{padding:0.2em 0.8em;font-size:145%;line-height:1.2em}.mw-parser-output .sidebar-title-with-pretitle{padding:0.1em 0.4em}.mw-parser-output .sidebar-image{padding:0.2em 0.4em 0.4em}.mw-parser-output .sidebar-heading{padding:0.1em 0.4em}.mw-parser-output .sidebar-content{padding:0 0.5em 0.4em}.mw-parser-output .sidebar-content-with-subgroup{padding:0.1em 0.4em 0.2em}.mw-parser-output .sidebar-above,.mw-parser-output .sidebar-below{padding:0.3em 0.8em;font-weight:bold}.mw-parser-output .sidebar-collapse .sidebar-above,.mw-parser-output .sidebar-collapse .sidebar-below{border-top:1px solid #aaa;border-bottom:1px solid #aaa}.mw-parser-output .sidebar-navbar{text-align:right;font-size:115%;padding:0 0.4em 0.4em}.mw-parser-output .sidebar-list-title{padding:0 0.4em;text-align:left;font-weight:bold;line-height:1.6em;font-size:105%}.mw-parser-output .sidebar-list-title-c{padding:0 0.4em;text-align:center;margin:0 3.3em}@media(max-width:640px){body.mediawiki .mw-parser-output .sidebar{width:100%!important;clear:both;float:none!important;margin-left:0!important;margin-right:0!important}}body.skin--responsive .mw-parser-output .sidebar a>img{max-width:none!important}@media screen{html.skin-theme-clientpref-night .mw-parser-output .sidebar:not(.notheme) .sidebar-list-title,html.skin-theme-clientpref-night .mw-parser-output .sidebar:not(.notheme) .sidebar-title-with-pretitle{background:transparent!important}html.skin-theme-clientpref-night .mw-parser-output .sidebar:not(.notheme) .sidebar-title-with-pretitle a{color:var(--color-progressive)!important}}@media screen and (prefers-color-scheme:dark){html.skin-theme-clientpref-os .mw-parser-output .sidebar:not(.notheme) .sidebar-list-title,html.skin-theme-clientpref-os .mw-parser-output .sidebar:not(.notheme) .sidebar-title-with-pretitle{background:transparent!important}html.skin-theme-clientpref-os .mw-parser-output .sidebar:not(.notheme) .sidebar-title-with-pretitle a{color:var(--color-progressive)!important}}@media print{body.ns-0 .mw-parser-output .sidebar{display:none!important}}

/* end https://en.wikipedia.org/ */

</style><style data-mw-deduplicate="TemplateStyles:r886047488">

/* start https://en.wikipedia.org/ */

.mw-parser-output .nobold{font-weight:normal}

/* end https://en.wikipedia.org/ */

</style><table class="sidebar sidebar-collapse nomobile nowraplinks"><tbody><tr><td class="sidebar-pretitle">Part of a series on</td></tr><tr><th class="sidebar-title-with-pretitle"><a href="Machine_learning" title="Machine learning">Machine learning</a><br>and <a href="Data_mining" title="Data mining">data mining</a></th></tr><tr><td class="sidebar-content">

<ul><li><a href="Supervised_learning" title="Supervised learning">Supervised learning</a></li>

<li><a href="Unsupervised_learning" title="Unsupervised learning">Unsupervised learning</a></li>

<li><a href="Semi-supervised_learning" class="mw-redirect" title="Semi-supervised learning">Semi-supervised learning</a></li>

<li><a href="Self-supervised_learning" title="Self-supervised learning">Self-supervised learning</a></li>

<li><a href="Reinforcement_learning" title="Reinforcement learning">Reinforcement learning</a></li>

<li><a href="Meta-learning_(computer_science)" title="Meta-learning (computer science)">Meta-learning</a></li>

<li><a href="Online_machine_learning" title="Online machine learning">Online learning</a></li>

<li><a href="Batch_learning" class="mw-redirect" title="Batch learning">Batch learning</a></li>

<li><a href="Curriculum_learning" title="Curriculum learning">Curriculum learning</a></li>

<li><a href="Rule-based_machine_learning" title="Rule-based machine learning">Rule-based learning</a></li>

<li><a href="Neuro-symbolic_AI" title="Neuro-symbolic AI">Neuro-symbolic AI</a></li>

<li><a href="Neuromorphic_engineering" class="mw-redirect" title="Neuromorphic engineering">Neuromorphic engineering</a></li>

<li><a href="Quantum_machine_learning" title="Quantum machine learning">Quantum machine learning</a></li></ul></div></div></td>

</tr><tr><td class="sidebar-content">

<ul><li><a href="Statistical_classification" title="Statistical classification">Classification</a></li>

<li><a href="Generative_model" title="Generative model">Generative modeling</a></li>

<li><a href="Regression_analysis" title="Regression analysis">Regression</a></li>

<li><a href="Cluster_analysis" title="Cluster analysis">Clustering</a></li>

<li><a href="Dimensionality_reduction" title="Dimensionality reduction">Dimensionality reduction</a></li>

<li><a href="Density_estimation" title="Density estimation">Density estimation</a></li>

<li><a href="Anomaly_detection" title="Anomaly detection">Anomaly detection</a></li>

<li><a href="Data_cleaning" class="mw-redirect" title="Data cleaning">Data cleaning</a></li>

<li><a href="Automated_machine_learning" title="Automated machine learning">AutoML</a></li>

<li><a href="Association_rule_learning" title="Association rule learning">Association rules</a></li>

<li><a href="Semantic_analysis_(machine_learning)" title="Semantic analysis (machine learning)">Semantic analysis</a></li>

<li><a href="Structured_prediction" title="Structured prediction">Structured prediction</a></li>

<li><a href="Feature_engineering" title="Feature engineering">Feature engineering</a></li>

<li><a href="Feature_learning" title="Feature learning">Feature learning</a></li>

<li><a href="Learning_to_rank" title="Learning to rank">Learning to rank</a></li>

<li><a href="Grammar_induction" title="Grammar induction">Grammar induction</a></li>

<li><a href="Ontology_learning" title="Ontology learning">Ontology learning</a></li>

<li><a href="Multimodal_learning" title="Multimodal learning">Multimodal learning</a></li></ul></div></div></td>

</tr><tr><td class="sidebar-content">

<div class="sidebar-list mw-collapsible mw-collapsed machine-learning-list-title"><div class="sidebar-list-title" style="border-top:1px solid #aaa; text-align:center;;color: var(--color-base)"><div style="display: inline-block; line-height: 1.2em; padding: .1em 0;"><a href="Supervised_learning" title="Supervised learning">Supervised learning</a><br><span class="nobold"><span style="font-size: 85%;">(<b><a href="Statistical_classification" title="Statistical classification">classification</a></b> • <b><a href="Regression_analysis" title="Regression analysis">regression</a></b>)</span></span> </div></div><div class="sidebar-list-content mw-collapsible-content hlist">

<ul><li><a href="Apprenticeship_learning" title="Apprenticeship learning">Apprenticeship learning</a></li>

<li><a href="Decision_tree_learning" title="Decision tree learning">Decision trees</a></li>

<li><a href="Ensemble_learning" title="Ensemble learning">Ensembles</a>

<ul><li><a href="Bootstrap_aggregating" title="Bootstrap aggregating">Bagging</a></li>

<li><a href="Boosting_(machine_learning)" title="Boosting (machine learning)">Boosting</a></li>

<li><a href="Random_forest" title="Random forest">Random forest</a></li></ul></li>

<li><a href="Linear_regression" title="Linear regression">Linear regression</a></li>

<li><a href="Naive_Bayes_classifier" title="Naive Bayes classifier">Naive Bayes</a></li>

<li><a href="Artificial_neural_network" class="mw-redirect" title="Artificial neural network">Artificial neural networks</a></li>

<li><a href="Logistic_regression" title="Logistic regression">Logistic regression</a></li>

<li><a href="Perceptron" title="Perceptron">Perceptron</a></li>

<li><a href="Relevance_vector_machine" title="Relevance vector machine">Relevance vector machine (RVM)</a></li>

<li><a href="Support_vector_machine" title="Support vector machine">Support vector machine (SVM)</a></li></ul></div></div></td>

</tr><tr><td class="sidebar-content">

<div class="sidebar-list mw-collapsible mw-collapsed machine-learning-list-title"><div class="sidebar-list-title" style="border-top:1px solid #aaa; text-align:center;;color: var(--color-base)"><a href="Cluster_analysis" title="Cluster analysis">Clustering</a></div><div class="sidebar-list-content mw-collapsible-content hlist">

<ul><li><a href="BIRCH" title="BIRCH">BIRCH</a></li>

<li><a href="Hierarchical_clustering" title="Hierarchical clustering">Hierarchical</a></li>

<li><a href="K-means_clustering" title="K-means clustering"><i>k</i>-means</a></li>

<li><a href="Fuzzy_clustering" title="Fuzzy clustering">Fuzzy</a></li>

<li><a href="Expectation%E2%80%93maximization_algorithm" title="Expectation–maximization algorithm">Expectation–maximization (EM)</a></li>

<li><br><a href="DBSCAN" title="DBSCAN">DBSCAN</a></li>

<li><a href="OPTICS_algorithm" title="OPTICS algorithm">OPTICS</a></li>

<li><a href="Mean_shift" title="Mean shift">Mean shift</a></li></ul></div></div></td>

</tr><tr><td class="sidebar-content">

<div class="sidebar-list mw-collapsible mw-collapsed machine-learning-list-title"><div class="sidebar-list-title" style="border-top:1px solid #aaa; text-align:center;;color: var(--color-base)"><a href="Dimensionality_reduction" title="Dimensionality reduction">Dimensionality reduction</a></div><div class="sidebar-list-content mw-collapsible-content hlist">

<ul><li><a href="Factor_analysis" title="Factor analysis">Factor analysis</a></li>

</tr><tr><td class="sidebar-content">

<div class="sidebar-list mw-collapsible mw-collapsed machine-learning-list-title"><div class="sidebar-list-title" style="border-top:1px solid #aaa; text-align:center;;color: var(--color-base)"><a href="Structured_prediction" title="Structured prediction">Structured prediction</a></div><div class="sidebar-list-content mw-collapsible-content hlist">

<ul><li><a href="Graphical_model" title="Graphical model">Graphical models</a>

<ul><li><a href="Bayesian_network" title="Bayesian network">Bayes net</a></li>

<li><a href="Conditional_random_field" title="Conditional random field">Conditional random field</a></li>

<li><a href="Hidden_Markov_model" title="Hidden Markov model">Hidden Markov</a></li></ul></li></ul></div></div></td>

</tr><tr><td class="sidebar-content">

<div class="sidebar-list mw-collapsible mw-collapsed machine-learning-list-title"><div class="sidebar-list-title" style="border-top:1px solid #aaa; text-align:center;;color: var(--color-base)"><a href="Anomaly_detection" title="Anomaly detection">Anomaly detection</a></div><div class="sidebar-list-content mw-collapsible-content hlist">

<ul><li><a href="Random_sample_consensus" title="Random sample consensus">RANSAC</a></li>

<li><a href="Local_outlier_factor" title="Local outlier factor">Local outlier factor</a></li>

<li><a href="Isolation_forest" title="Isolation forest">Isolation forest</a></li></ul></div></div></td>

</tr><tr><td class="sidebar-content">

<div class="sidebar-list mw-collapsible mw-collapsed machine-learning-list-title"><div class="sidebar-list-title" style="border-top:1px solid #aaa; text-align:center;;color: var(--color-base)"><a href="Neural_network_(machine_learning)" title="Neural network (machine learning)">Neural networks</a></div><div class="sidebar-list-content mw-collapsible-content hlist">

<ul><li><a href="Autoencoder" title="Autoencoder">Autoencoder</a></li>

<li><a href="Deep_learning" title="Deep learning">Deep learning</a></li>

<li><a href="Feedforward_neural_network" title="Feedforward neural network">Feedforward neural network</a></li>

<li><a href="Recurrent_neural_network" title="Recurrent neural network">Recurrent neural network</a>

<li><a href="Reservoir_computing" title="Reservoir computing">reservoir computing</a></li></ul></li>

<li><a href="Boltzmann_machine" title="Boltzmann machine">Boltzmann machine</a>

<ul><li><a href="Restricted_Boltzmann_machine" title="Restricted Boltzmann machine">Restricted</a></li></ul></li>

<li><a href="Diffusion_model" title="Diffusion model">Diffusion model</a></li>

<li><a href="Convolutional_neural_network" title="Convolutional neural network">Convolutional neural network</a>

<li><a href="LeNet" title="LeNet">LeNet</a></li>

<li><a href="AlexNet" title="AlexNet">AlexNet</a></li>

<li><a href="DeepDream" title="DeepDream">DeepDream</a></li></ul></li>

<li><a href="Neural_field" title="Neural field">Neural field</a>

<ul><li><a href="Neural_radiance_field" title="Neural radiance field">Neural radiance field</a></li>

<li><a href="Physics-informed_neural_networks" title="Physics-informed neural networks">Physics-informed neural networks</a></li></ul></li>

<li><a href="Transformer_(deep_learning_architecture)" title="Transformer (deep learning architecture)">Transformer</a>

<ul><li><a href="Vision_transformer" title="Vision transformer">Vision</a></li></ul></li>

<li><a href="Mamba_(deep_learning_architecture)" title="Mamba (deep learning architecture)">Mamba</a></li>

<li><a href="Spiking_neural_network" title="Spiking neural network">Spiking neural network</a></li>

<li><a href="Memtransistor" title="Memtransistor">Memtransistor</a></li>

<li><a href="Electrochemical_RAM" title="Electrochemical RAM">Electrochemical RAM</a> (ECRAM)</li></ul></div></div></td>

</tr><tr><td class="sidebar-content">

<div class="sidebar-list mw-collapsible mw-collapsed machine-learning-list-title"><div class="sidebar-list-title" style="border-top:1px solid #aaa; text-align:center;;color: var(--color-base)"><a href="Reinforcement_learning" title="Reinforcement learning">Reinforcement learning</a></div><div class="sidebar-list-content mw-collapsible-content hlist">

<ul><li><a href="Q-learning" title="Q-learning">Q-learning</a></li>

<li><a href="Policy_gradient_method" title="Policy gradient method">Policy gradient</a></li>

<li><a href="State%E2%80%93action%E2%80%93reward%E2%80%93state%E2%80%93action" title="State–action–reward–state–action">SARSA</a></li>

<li><a href="Temporal_difference_learning" title="Temporal difference learning">Temporal difference (TD)</a></li>

<li><a href="Multi-agent_reinforcement_learning" title="Multi-agent reinforcement learning">Multi-agent</a>

</tr><tr><td class="sidebar-content">

<ul><li><a href="Active_learning_(machine_learning)" title="Active learning (machine learning)">Active learning</a></li>

<li><a href="Crowdsourcing" title="Crowdsourcing">Crowdsourcing</a></li>

<li><a href="Human-in-the-loop" title="Human-in-the-loop">Human-in-the-loop</a></li>

<li><a href="Mechanistic_interpretability" title="Mechanistic interpretability">Mechanistic interpretability</a></li>

</tr><tr><td class="sidebar-content">

<ul><li><a href="Coefficient_of_determination" title="Coefficient of determination">Coefficient of determination</a></li>

<li><a href="Confusion_matrix" title="Confusion matrix">Confusion matrix</a></li>

<li><a href="Learning_curve_(machine_learning)" title="Learning curve (machine learning)">Learning curve</a></li>

<li><a href="Receiver_operating_characteristic" title="Receiver operating characteristic">ROC curve</a></li></ul></div></div></td>

</tr><tr><td class="sidebar-content">

<div class="sidebar-list mw-collapsible mw-collapsed machine-learning-list-title"><div class="sidebar-list-title" style="border-top:1px solid #aaa; text-align:center;;color: var(--color-base)">Mathematical foundations</div><div class="sidebar-list-content mw-collapsible-content hlist">

<ul><li><a href="Kernel_machines" class="mw-redirect" title="Kernel machines">Kernel machines</a></li>

<li><a href="Bias%E2%80%93variance_tradeoff" title="Bias–variance tradeoff">Bias–variance tradeoff</a></li>

<li><a href="Computational_learning_theory" title="Computational learning theory">Computational learning theory</a></li>

<li><a href="Empirical_risk_minimization" title="Empirical risk minimization">Empirical risk minimization</a></li>

<li><a href="Occam_learning" title="Occam learning">Occam learning</a></li>

<li><a href="Probably_approximately_correct_learning" title="Probably approximately correct learning">PAC learning</a></li>

<li><a href="Statistical_learning_theory" title="Statistical learning theory">Statistical learning</a></li>

<li><a href="Vapnik%E2%80%93Chervonenkis_theory" title="Vapnik–Chervonenkis theory">VC theory</a></li>

<li><a href="Topological_deep_learning" title="Topological deep learning">Topological deep learning</a></li></ul></div></div></td>

</tr><tr><td class="sidebar-content">

<div class="sidebar-list mw-collapsible mw-collapsed machine-learning-list-title"><div class="sidebar-list-title" style="border-top:1px solid #aaa; text-align:center;;color: var(--color-base)">Journals and conferences</div><div class="sidebar-list-content mw-collapsible-content hlist">

<li><a href="Conference_on_Neural_Information_Processing_Systems" title="Conference on Neural Information Processing Systems">NeurIPS</a></li>

<li><a href="International_Joint_Conference_on_Artificial_Intelligence" title="International Joint Conference on Artificial Intelligence">IJCAI</a></li>

</tr><tr><td class="sidebar-content">

<ul><li><a href="Glossary_of_artificial_intelligence" title="Glossary of artificial intelligence">Glossary of artificial intelligence</a></li>

<li><a href="List_of_datasets_for_machine-learning_research" title="List of datasets for machine-learning research">List of datasets for machine-learning research</a>

<ul><li><a href="List_of_datasets_in_computer_vision_and_image_processing" title="List of datasets in computer vision and image processing">List of datasets in computer vision and image processing</a></li></ul></li>

<li><a href="Outline_of_machine_learning" title="Outline of machine learning">Outline of machine learning</a></li></ul></div></div></td>

</tr><tr><td class="sidebar-navbar"><style data-mw-deduplicate="TemplateStyles:r1239400231">

/* start https://en.wikipedia.org/ */

.mw-parser-output .navbar{display:inline;font-size:88%;font-weight:normal}.mw-parser-output .navbar-collapse{float:left;text-align:left}.mw-parser-output .navbar-boxtext{word-spacing:0}.mw-parser-output .navbar ul{display:inline-block;white-space:nowrap;line-height:inherit}.mw-parser-output .navbar-brackets::before{margin-right:-0.125em;content:"[ "}.mw-parser-output .navbar-brackets::after{margin-left:-0.125em;content:" ]"}.mw-parser-output .navbar li{word-spacing:-0.125em}.mw-parser-output .navbar a>span,.mw-parser-output .navbar a>abbr{text-decoration:inherit}.mw-parser-output .navbar-mini abbr{font-variant:small-caps;border-bottom:none;text-decoration:none;cursor:inherit}.mw-parser-output .navbar-ct-full{font-size:114%;margin:0 7em}.mw-parser-output .navbar-ct-mini{font-size:114%;margin:0 4em}html.skin-theme-clientpref-night .mw-parser-output .navbar li a abbr{color:var(--color-base)!important}@media(prefers-color-scheme:dark){html.skin-theme-clientpref-os .mw-parser-output .navbar li a abbr{color:var(--color-base)!important}}@media print{.mw-parser-output .navbar{display:none!important}}

/* end https://en.wikipedia.org/ */

</style></td></tr></tbody></table>

<p><b>TensorFlow</b> is a <a href="Library_(computing)" title="Library (computing)">software library</a> for <a href="Machine_learning" title="Machine learning">machine learning</a> and <a href="Artificial_intelligence" title="Artificial intelligence">artificial intelligence</a>. It can be used across a range of tasks, but is used mainly for <a href="Types_of_artificial_neural_networks#Training" title="Types of artificial neural networks">training</a> and <a href="Statistical_inference" title="Statistical inference">inference</a> of <a href="Neural_network_(machine_learning)" title="Neural network (machine learning)">neural networks</a>.<sup id="cite_ref-3" class="reference"><a href="#cite_note-3"><span class="cite-bracket">[</span>3<span class="cite-bracket">]</span></a></sup><sup id="cite_ref-YoutubeClip_4-0" class="reference"><a href="#cite_note-YoutubeClip-4"><span class="cite-bracket">[</span>4<span class="cite-bracket">]</span></a></sup> It is one of the most popular <a href="Deep_learning" title="Deep learning">deep learning</a> frameworks, alongside others such as <a href="PyTorch" title="PyTorch">PyTorch</a>.<sup id="cite_ref-5" class="reference"><a href="#cite_note-5"><span class="cite-bracket">[</span>5<span class="cite-bracket">]</span></a></sup> It is <a href="Free_and_open-source_software" title="Free and open-source software">free and open-source software</a> released under the <a href="Apache_License_2.0" class="mw-redirect" title="Apache License 2.0">Apache License 2.0</a>.

</p><p>It was developed by the <a href="Google_Brain" title="Google Brain">Google Brain</a> team for <a href="Google" title="Google">Google</a>'s internal use in research and production.<sup id="cite_ref-6" class="reference"><a href="#cite_note-6"><span class="cite-bracket">[</span>6<span class="cite-bracket">]</span></a></sup><sup id="cite_ref-7" class="reference"><a href="#cite_note-7"><span class="cite-bracket">[</span>7<span class="cite-bracket">]</span></a></sup><sup id="cite_ref-8" class="reference"><a href="#cite_note-8"><span class="cite-bracket">[</span>8<span class="cite-bracket">]</span></a></sup> The initial version was released under the <a href="Apache_License_2.0" class="mw-redirect" title="Apache License 2.0">Apache License 2.0</a> in 2015.<sup id="cite_ref-Credits_1-1" class="reference"><a href="#cite_note-Credits-1"><span class="cite-bracket">[</span>1<span class="cite-bracket">]</span></a></sup><sup id="cite_ref-Metz-Nov9_9-0" class="reference"><a href="#cite_note-Metz-Nov9-9"><span class="cite-bracket">[</span>9<span class="cite-bracket">]</span></a></sup> Google released an updated version, TensorFlow 2.0, in September 2019.<sup id="cite_ref-:12_10-0" class="reference"><a href="#cite_note-:12-10"><span class="cite-bracket">[</span>10<span class="cite-bracket">]</span></a></sup>

</p><p>TensorFlow can be used in a wide variety of programming languages, including <a href="Python_(programming_language)" title="Python (programming language)">Python</a>, <a href="JavaScript" title="JavaScript">JavaScript</a>, <a href="C%2B%2B" title="C++">C++</a>, and <a href="Java_(programming_language)" title="Java (programming language)">Java</a>,<sup id="cite_ref-:13_11-0" class="reference"><a href="#cite_note-:13-11"><span class="cite-bracket">[</span>11<span class="cite-bracket">]</span></a></sup> facilitating its use in a range of applications in many sectors.

</p>

<div class="mw-heading mw-heading2"><h2 id="History">History</h2></div>

<div class="mw-heading mw-heading3"><h3 id="DistBelief">DistBelief</h3></div>

<p>Starting in 2011, Google Brain built DistBelief as a <a href="Proprietary_software" title="Proprietary software">proprietary</a> <a href="Machine_learning" title="Machine learning">machine learning</a> system based on <a href="Deep_learning" title="Deep learning">deep learning</a> <a href="Artificial_neural_network" class="mw-redirect" title="Artificial neural network">neural networks</a>. Its use grew rapidly across diverse <a href="Alphabet_Inc." title="Alphabet Inc.">Alphabet</a> companies in both research and commercial applications.<sup id="cite_ref-whitepaper2015_12-0" class="reference"><a href="#cite_note-whitepaper2015-12"><span class="cite-bracket">[</span>12<span class="cite-bracket">]</span></a></sup><sup id="cite_ref-Perez_13-0" class="reference"><a href="#cite_note-Perez-13"><span class="cite-bracket">[</span>13<span class="cite-bracket">]</span></a></sup> Google assigned multiple computer scientists, including <a href="Jeff_Dean_(computer_scientist)" class="mw-redirect" title="Jeff Dean (computer scientist)">Jeff Dean</a>, to simplify and <a href="Code_refactoring" title="Code refactoring">refactor</a> the codebase of DistBelief into a faster, more robust application-grade library, which became TensorFlow.<sup id="cite_ref-Oremus_14-0" class="reference"><a href="#cite_note-Oremus-14"><span class="cite-bracket">[</span>14<span class="cite-bracket">]</span></a></sup> In 2009, the team, led by <a href="Geoffrey_Hinton" title="Geoffrey Hinton">Geoffrey Hinton</a>, had implemented generalized <a href="Backpropagation" title="Backpropagation">backpropagation</a> and other improvements, which allowed generation of <a href="Neural_network" title="Neural network">neural networks</a> with substantially higher accuracy, for instance a 25% reduction in errors in <a href="Speech_recognition" title="Speech recognition">speech recognition</a>.<sup id="cite_ref-Ward-Bailey_15-0" class="reference"><a href="#cite_note-Ward-Bailey-15"><span class="cite-bracket">[</span>15<span class="cite-bracket">]</span></a></sup>

</p>

<div class="mw-heading mw-heading3"><h3 id="TensorFlow">TensorFlow</h3></div>

<p>TensorFlow is Google Brain's second-generation system. Version 1.0.0 was released on February 11, 2017.<sup id="cite_ref-16" class="reference"><a href="#cite_note-16"><span class="cite-bracket">[</span>16<span class="cite-bracket">]</span></a></sup> While the <a href="Reference_implementation" title="Reference implementation">reference implementation</a> runs on single devices, TensorFlow can run on multiple <a href="Central_processing_unit" title="Central processing unit">CPUs</a> and <a href="GPU" class="mw-redirect" title="GPU">GPUs</a> (with optional <a href="CUDA" title="CUDA">CUDA</a> and <a href="SYCL" title="SYCL">SYCL</a> extensions for <a href="General-purpose_computing_on_graphics_processing_units" title="General-purpose computing on graphics processing units">general-purpose computing on graphics processing units</a>).<sup id="cite_ref-Metz-Nov10_17-0" class="reference"><a href="#cite_note-Metz-Nov10-17"><span class="cite-bracket">[</span>17<span class="cite-bracket">]</span></a></sup> TensorFlow is available on 64-bit <a href="Linux" title="Linux">Linux</a>, <a href="MacOS" title="MacOS">macOS</a>, <a href="Windows" class="mw-redirect" title="Windows">Windows</a>, and mobile computing platforms including <a href="Android_(operating_system)" title="Android (operating system)">Android</a> and <a href="IOS" title="IOS">iOS</a>.<sup id="cite_ref-18" class="reference"><a href="#cite_note-18"><span class="cite-bracket">[</span>18<span class="cite-bracket">]</span></a></sup><sup id="cite_ref-19" class="reference"><a href="#cite_note-19"><span class="cite-bracket">[</span>19<span class="cite-bracket">]</span></a></sup>

</p><p>Its flexible architecture allows for easy deployment of computation across a variety of platforms (CPUs, GPUs, <a href="Tensor_processing_unit" class="mw-redirect" title="Tensor processing unit">TPUs</a>), and from desktops to clusters of servers to mobile and <a href="Edge_device" title="Edge device">edge devices</a>.

</p><p>TensorFlow computations are expressed as <a href="State_(computer_science)" title="State (computer science)">stateful</a> <a href="Dataflow_programming" title="Dataflow programming">dataflow</a> <a href="Directed_graph" title="Directed graph">graphs</a>. The name TensorFlow derives from the operations that such neural networks perform on multidimensional data arrays, which are referred to as <i><a href="Tensor_(machine_learning)" title="Tensor (machine learning)">tensors</a></i>.<sup id="cite_ref-20" class="reference"><a href="#cite_note-20"><span class="cite-bracket">[</span>20<span class="cite-bracket">]</span></a></sup> During the <a href="Google_I/O" title="Google I/O">Google I/O Conference</a> in June 2016, Jeff Dean stated that 1,500 repositories on <a href="GitHub" title="GitHub">GitHub</a> mentioned TensorFlow, of which only 5 were from Google.<sup id="cite_ref-1500repo's_21-0" class="reference"><a href="#cite_note-1500repo's-21"><span class="cite-bracket">[</span>21<span class="cite-bracket">]</span></a></sup>

</p><p>In March 2018, Google announced TensorFlow.js version 1.0 for machine learning in <a href="JavaScript" title="JavaScript">JavaScript</a>.<sup id="cite_ref-22" class="reference"><a href="#cite_note-22"><span class="cite-bracket">[</span>22<span class="cite-bracket">]</span></a></sup>

</p><p>In Jan 2019, Google announced TensorFlow 2.0.<sup id="cite_ref-23" class="reference"><a href="#cite_note-23"><span class="cite-bracket">[</span>23<span class="cite-bracket">]</span></a></sup> It became officially available in September 2019.<sup id="cite_ref-:12_10-1" class="reference"><a href="#cite_note-:12-10"><span class="cite-bracket">[</span>10<span class="cite-bracket">]</span></a></sup>

</p><p>In May 2019, Google announced TensorFlow Graphics for deep learning in computer graphics.<sup id="cite_ref-24" class="reference"><a href="#cite_note-24"><span class="cite-bracket">[</span>24<span class="cite-bracket">]</span></a></sup>

</p>

<div class="mw-heading mw-heading3"><h3 id="Tensor_processing_unit_(TPU)">Tensor processing unit (TPU)</h3></div>

/* start https://en.wikipedia.org/ */

.mw-parser-output .hatnote{font-style:italic}.mw-parser-output div.hatnote{padding-left:1.6em;margin-bottom:0.5em}.mw-parser-output .hatnote i{font-style:normal}.mw-parser-output .hatnote+link+.hatnote{margin-top:-0.5em}@media print{body.ns-0 .mw-parser-output .hatnote{display:none!important}}

/* end https://en.wikipedia.org/ */

</style><div role="note" class="hatnote navigation-not-searchable">Main article: <a href="Tensor_processing_unit" class="mw-redirect" title="Tensor processing unit">Tensor processing unit</a></div>

<p>In May 2016, Google announced its <a href="Tensor_processing_unit" class="mw-redirect" title="Tensor processing unit">Tensor processing unit</a> (TPU), an <a href="Application-specific_integrated_circuit" title="Application-specific integrated circuit">application-specific integrated circuit</a> (<a href="Application-specific_integrated_circuit" title="Application-specific integrated circuit">ASIC</a>, a hardware chip) built specifically for machine learning and tailored for TensorFlow. A TPU is a programmable <a href="AI_accelerator_(computer_hardware)" class="mw-redirect" title="AI accelerator (computer hardware)">AI accelerator</a> designed to provide high <a href="Throughput" class="mw-redirect" title="Throughput">throughput</a> of low-precision <a href="Arithmetic" title="Arithmetic">arithmetic</a> (e.g., <a href="8-bit" class="mw-redirect" title="8-bit">8-bit</a>), and oriented toward using or running models rather than <a href="Supervised_learning" title="Supervised learning">training</a> them. Google announced they had been running TPUs inside their data centers for more than a year, and had found them to deliver an <a href="Order_of_magnitude" title="Order of magnitude">order of magnitude</a> better-optimized <a href="Performance_per_watt" title="Performance per watt">performance per watt</a> for machine learning.<sup id="cite_ref-25" class="reference"><a href="#cite_note-25"><span class="cite-bracket">[</span>25<span class="cite-bracket">]</span></a></sup>

</p><p>In May 2017, Google announced the second-generation, as well as the availability of the TPUs in <a href="Google_Compute_Engine" title="Google Compute Engine">Google Compute Engine</a>.<sup id="cite_ref-26" class="reference"><a href="#cite_note-26"><span class="cite-bracket">[</span>26<span class="cite-bracket">]</span></a></sup> The second-generation TPUs deliver up to 180 <a href="FLOPS" class="mw-redirect" title="FLOPS">teraflops</a> of performance, and when organized into clusters of 64 TPUs, provide up to 11.5 <a href="FLOPS" class="mw-redirect" title="FLOPS">petaflops</a>.

</p><p>In May 2018, Google announced the third-generation TPUs delivering up to 420 <a href="FLOPS" class="mw-redirect" title="FLOPS">teraflops</a> of performance and 128 GB high <a href="Bandwidth_(computing)" title="Bandwidth (computing)">bandwidth</a> memory (HBM). Cloud TPU v3 Pods offer 100+ <a href="FLOPS" class="mw-redirect" title="FLOPS">petaflops</a> of performance and 32 TB HBM.<sup id="cite_ref-27" class="reference"><a href="#cite_note-27"><span class="cite-bracket">[</span>27<span class="cite-bracket">]</span></a></sup>

</p><p>In February 2018, Google announced that they were making TPUs available in beta on the <a href="Google_Cloud_Platform" title="Google Cloud Platform">Google Cloud Platform</a>.<sup id="cite_ref-28" class="reference"><a href="#cite_note-28"><span class="cite-bracket">[</span>28<span class="cite-bracket">]</span></a></sup>

</p>

<p>In July 2018, the Edge TPU was announced. Edge TPU is Google's purpose-built <a href="Application-specific_integrated_circuit" title="Application-specific integrated circuit">ASIC</a> chip designed to run TensorFlow Lite machine learning (ML) models on small client computing devices such as smartphones<sup id="cite_ref-29" class="reference"><a href="#cite_note-29"><span class="cite-bracket">[</span>29<span class="cite-bracket">]</span></a></sup> known as <a href="Edge_computing" title="Edge computing">edge computing</a>.

</p>

<div class="mw-heading mw-heading3"><h3 id="TensorFlow_Lite">TensorFlow Lite</h3></div>

<p>In May 2017, Google announced a software stack specifically for mobile development, TensorFlow Lite.<sup id="cite_ref-30" class="reference"><a href="#cite_note-30"><span class="cite-bracket">[</span>30<span class="cite-bracket">]</span></a></sup> In January 2019, the TensorFlow team released a developer preview of the mobile GPU inference engine with OpenGL ES 3.1 Compute Shaders on Android devices and Metal Compute Shaders on iOS devices.<sup id="cite_ref-31" class="reference"><a href="#cite_note-31"><span class="cite-bracket">[</span>31<span class="cite-bracket">]</span></a></sup> In May 2019, Google announced that their TensorFlow Lite Micro (also known as TensorFlow Lite for Microcontrollers) and <a href="Arm_Holdings" title="Arm Holdings">ARM's</a> uTensor would be merging.<sup id="cite_ref-32" class="reference"><a href="#cite_note-32"><span class="cite-bracket">[</span>32<span class="cite-bracket">]</span></a></sup>

</p>

<div class="mw-heading mw-heading3"><h3 id="TensorFlow_2.0">TensorFlow 2.0</h3></div>

<p>As TensorFlow's market share among research papers was declining to the advantage of <a href="PyTorch" title="PyTorch">PyTorch</a>,<sup id="cite_ref-:9_33-0" class="reference"><a href="#cite_note-:9-33"><span class="cite-bracket">[</span>33<span class="cite-bracket">]</span></a></sup> the TensorFlow Team announced a release of a new major version of the library in September 2019. TensorFlow 2.0 introduced many changes, the most significant being TensorFlow eager, which changed the automatic differentiation scheme from the static computational graph to the "Define-by-Run" scheme originally made popular by <a href="Chainer" title="Chainer">Chainer</a> and later <a href="PyTorch" title="PyTorch">PyTorch</a>.<sup id="cite_ref-:9_33-1" class="reference"><a href="#cite_note-:9-33"><span class="cite-bracket">[</span>33<span class="cite-bracket">]</span></a></sup> Other major changes included removal of old libraries, cross-compatibility between trained models on different versions of TensorFlow, and significant improvements to the performance on GPU.<sup id="cite_ref-“introduction”_34-0" class="reference"><a href="#cite_note-“introduction”-34"><span class="cite-bracket">[</span>34<span class="cite-bracket">]</span></a></sup>

</p>

<div class="mw-heading mw-heading2"><h2 id="Features">Features</h2></div>

<div class="mw-heading mw-heading3"><h3 id="AutoDifferentiation">AutoDifferentiation</h3></div>

<p><a href="Automatic_differentiation" title="Automatic differentiation">AutoDifferentiation</a> is the process of automatically calculating the gradient vector of a model with respect to each of its parameters. With this feature, TensorFlow can automatically compute the gradients for the parameters in a model, which is useful to algorithms such as <a href="Backpropagation" title="Backpropagation">backpropagation</a> which require gradients to optimize performance.<sup id="cite_ref-:0_35-0" class="reference"><a href="#cite_note-:0-35"><span class="cite-bracket">[</span>35<span class="cite-bracket">]</span></a></sup> To do so, the framework must keep track of the order of operations done to the input Tensors in a model, and then compute the gradients with respect to the appropriate parameters.<sup id="cite_ref-:0_35-1" class="reference"><a href="#cite_note-:0-35"><span class="cite-bracket">[</span>35<span class="cite-bracket">]</span></a></sup>

</p>

<div class="mw-heading mw-heading3"><h3 id="Eager_execution">Eager execution</h3></div>

<p>TensorFlow includes an “eager execution” mode, which means that operations are evaluated immediately as opposed to being added to a computational graph which is executed later.<sup id="cite_ref-:3_36-0" class="reference"><a href="#cite_note-:3-36"><span class="cite-bracket">[</span>36<span class="cite-bracket">]</span></a></sup> Code executed eagerly can be examined step-by step-through a debugger, since data is augmented at each line of code rather than later in a computational graph.<sup id="cite_ref-:3_36-1" class="reference"><a href="#cite_note-:3-36"><span class="cite-bracket">[</span>36<span class="cite-bracket">]</span></a></sup> This execution paradigm is considered to be easier to debug because of its step by step transparency.<sup id="cite_ref-:3_36-2" class="reference"><a href="#cite_note-:3-36"><span class="cite-bracket">[</span>36<span class="cite-bracket">]</span></a></sup>

</p>

<div class="mw-heading mw-heading3"><h3 id="Distribute">Distribute</h3></div>

<p>In both eager and graph executions, TensorFlow provides an API for distributing computation across multiple devices with various distribution strategies.<sup id="cite_ref-:4_37-0" class="reference"><a href="#cite_note-:4-37"><span class="cite-bracket">[</span>37<span class="cite-bracket">]</span></a></sup> This <a href="Distributed_computing" title="Distributed computing">distributed computing</a> can often speed up the execution of training and evaluating of TensorFlow models and is a common practice in the field of AI.<sup id="cite_ref-:4_37-1" class="reference"><a href="#cite_note-:4-37"><span class="cite-bracket">[</span>37<span class="cite-bracket">]</span></a></sup><sup id="cite_ref-38" class="reference"><a href="#cite_note-38"><span class="cite-bracket">[</span>38<span class="cite-bracket">]</span></a></sup>

</p>

<div class="mw-heading mw-heading3"><h3 id="Losses">Losses</h3></div>

<p>To train and assess models, TensorFlow provides a set of <a href="Loss_function" title="Loss function">loss functions</a> (also known as <a href="Mathematical_optimization" title="Mathematical optimization">cost functions</a>).<sup id="cite_ref-:5_39-0" class="reference"><a href="#cite_note-:5-39"><span class="cite-bracket">[</span>39<span class="cite-bracket">]</span></a></sup> Some popular examples include <a href="Mean_squared_error" title="Mean squared error">mean squared error</a> (MSE) and <a href="Cross_entropy" class="mw-redirect" title="Cross entropy">binary cross entropy</a> (BCE).<sup id="cite_ref-:5_39-1" class="reference"><a href="#cite_note-:5-39"><span class="cite-bracket">[</span>39<span class="cite-bracket">]</span></a></sup>

</p>

<div class="mw-heading mw-heading3"><h3 id="Metrics">Metrics</h3></div>

<p>In order to assess the performance of machine learning models, TensorFlow gives API access to commonly used metrics. Examples include various accuracy metrics (binary, categorical, sparse categorical) along with other metrics such as <a href="Precision_and_recall" title="Precision and recall">Precision, Recall</a>, and <a href="Jaccard_index" title="Jaccard index">Intersection-over-Union</a> (IoU).<sup id="cite_ref-40" class="reference"><a href="#cite_note-40"><span class="cite-bracket">[</span>40<span class="cite-bracket">]</span></a></sup>

</p>

<p>TensorFlow.nn is a module for executing primitive <a href="Artificial_neural_network" class="mw-redirect" title="Artificial neural network">neural network</a> operations on models.<sup id="cite_ref-:10_41-0" class="reference"><a href="#cite_note-:10-41"><span class="cite-bracket">[</span>41<span class="cite-bracket">]</span></a></sup> Some of these operations include variations of <a href="Convolutional_neural_network" title="Convolutional neural network">convolutions</a> (1/2/3D, Atrous, depthwise), <a href="Activation_function" title="Activation function">activation functions</a> (<a href="Softmax_function" title="Softmax function">Softmax</a>, <a href="Rectifier_(neural_networks)" title="Rectifier (neural networks)">RELU</a>, GELU, <a href="Sigmoid_function" title="Sigmoid function">Sigmoid</a>, etc.) and their variations, and other operations (<a href="Max_pooling" class="mw-redirect" title="Max pooling">max-pooling</a>, bias-add, etc.).<sup id="cite_ref-:10_41-1" class="reference"><a href="#cite_note-:10-41"><span class="cite-bracket">[</span>41<span class="cite-bracket">]</span></a></sup>

</p>

<div class="mw-heading mw-heading3"><h3 id="Optimizers">Optimizers</h3></div>

<p>TensorFlow offers a set of optimizers for training neural networks, including <a href="Adam_(optimization_algorithm)" class="mw-redirect" title="Adam (optimization algorithm)">ADAM</a>, <a href="Adagrad" class="mw-redirect" title="Adagrad">ADAGRAD</a>, and <a href="Stochastic_gradient_descent" title="Stochastic gradient descent">Stochastic Gradient Descent</a> (SGD).<sup id="cite_ref-:11_42-0" class="reference"><a href="#cite_note-:11-42"><span class="cite-bracket">[</span>42<span class="cite-bracket">]</span></a></sup> When training a model, different optimizers offer different modes of parameter tuning, often affecting a model's convergence and performance.<sup id="cite_ref-43" class="reference"><a href="#cite_note-43"><span class="cite-bracket">[</span>43<span class="cite-bracket">]</span></a></sup>

</p>

<div class="mw-heading mw-heading2"><h2 id="Usage_and_extensions">Usage and extensions</h2></div>

<div class="mw-heading mw-heading3"><h3 id="TensorFlow_2">TensorFlow</h3></div>

<p>TensorFlow serves as a core platform and library for machine learning. TensorFlow's APIs use <a href="Keras" title="Keras">Keras</a> to allow users to make their own machine-learning models.<sup id="cite_ref-“introduction”_34-1" class="reference"><a href="#cite_note-“introduction”-34"><span class="cite-bracket">[</span>34<span class="cite-bracket">]</span></a></sup><sup id="cite_ref-44" class="reference"><a href="#cite_note-44"><span class="cite-bracket">[</span>44<span class="cite-bracket">]</span></a></sup> In addition to building and training their model, TensorFlow can also help load the data to train the model, and deploy it using TensorFlow Serving.<sup id="cite_ref-:1_45-0" class="reference"><a href="#cite_note-:1-45"><span class="cite-bracket">[</span>45<span class="cite-bracket">]</span></a></sup>

</p><p>TensorFlow provides a stable <a href="Python_(programming_language)" title="Python (programming language)">Python</a> <a href="API" title="API">Application Program Interface</a> (<a href="API" title="API">API</a>),<sup id="cite_ref-46" class="reference"><a href="#cite_note-46"><span class="cite-bracket">[</span>46<span class="cite-bracket">]</span></a></sup> as well as APIs without backwards compatibility guarantee for <a href="JavaScript" title="JavaScript">Javascript</a>,<sup id="cite_ref-47" class="reference"><a href="#cite_note-47"><span class="cite-bracket">[</span>47<span class="cite-bracket">]</span></a></sup> <a href="C%2B%2B" title="C++">C++</a>,<sup id="cite_ref-48" class="reference"><a href="#cite_note-48"><span class="cite-bracket">[</span>48<span class="cite-bracket">]</span></a></sup> and <a href="Java_(programming_language)" title="Java (programming language)">Java</a>.<sup id="cite_ref-49" class="reference"><a href="#cite_note-49"><span class="cite-bracket">[</span>49<span class="cite-bracket">]</span></a></sup><sup id="cite_ref-:13_11-1" class="reference"><a href="#cite_note-:13-11"><span class="cite-bracket">[</span>11<span class="cite-bracket">]</span></a></sup> Third-party language binding packages are also available for <a href="C_Sharp_(programming_language)" title="C Sharp (programming language)">C#</a>,<sup id="cite_ref-50" class="reference"><a href="#cite_note-50"><span class="cite-bracket">[</span>50<span class="cite-bracket">]</span></a></sup><sup id="cite_ref-51" class="reference"><a href="#cite_note-51"><span class="cite-bracket">[</span>51<span class="cite-bracket">]</span></a></sup> <a href="Haskell" title="Haskell">Haskell</a>,<sup id="cite_ref-52" class="reference"><a href="#cite_note-52"><span class="cite-bracket">[</span>52<span class="cite-bracket">]</span></a></sup> <a href="Julia_(programming_language)" title="Julia (programming language)">Julia</a>,<sup id="cite_ref-53" class="reference"><a href="#cite_note-53"><span class="cite-bracket">[</span>53<span class="cite-bracket">]</span></a></sup> <a href="MATLAB" title="MATLAB">MATLAB</a>,<sup id="cite_ref-54" class="reference"><a href="#cite_note-54"><span class="cite-bracket">[</span>54<span class="cite-bracket">]</span></a></sup> <a href="Object_Pascal" title="Object Pascal">Object Pascal</a>,<sup id="cite_ref-55" class="reference"><a href="#cite_note-55"><span class="cite-bracket">[</span>55<span class="cite-bracket">]</span></a></sup> <a href="R_(software)" class="mw-redirect" title="R (software)">R</a>,<sup id="cite_ref-56" class="reference"><a href="#cite_note-56"><span class="cite-bracket">[</span>56<span class="cite-bracket">]</span></a></sup> <a href="Scala_(programming_language)" title="Scala (programming language)">Scala</a>,<sup id="cite_ref-57" class="reference"><a href="#cite_note-57"><span class="cite-bracket">[</span>57<span class="cite-bracket">]</span></a></sup> <a href="Rust_(programming_language)" title="Rust (programming language)">Rust</a>,<sup id="cite_ref-58" class="reference"><a href="#cite_note-58"><span class="cite-bracket">[</span>58<span class="cite-bracket">]</span></a></sup> <a href="OCaml" title="OCaml">OCaml</a>,<sup id="cite_ref-59" class="reference"><a href="#cite_note-59"><span class="cite-bracket">[</span>59<span class="cite-bracket">]</span></a></sup> and <a href="Crystal_(programming_language)" title="Crystal (programming language)">Crystal</a>.<sup id="cite_ref-60" class="reference"><a href="#cite_note-60"><span class="cite-bracket">[</span>60<span class="cite-bracket">]</span></a></sup> Bindings that are now archived and unsupported include <a href="Go_(programming_language)" title="Go (programming language)">Go</a><sup id="cite_ref-61" class="reference"><a href="#cite_note-61"><span class="cite-bracket">[</span>61<span class="cite-bracket">]</span></a></sup> and <a href="Swift_(programming_language)" title="Swift (programming language)">Swift</a>.<sup id="cite_ref-62" class="reference"><a href="#cite_note-62"><span class="cite-bracket">[</span>62<span class="cite-bracket">]</span></a></sup>

</p>

<div class="mw-heading mw-heading3"><h3 id="TensorFlow.js">TensorFlow.js</h3></div>

<p>TensorFlow also has a library for machine learning in JavaScript. Using the provided <a href="JavaScript" title="JavaScript">JavaScript</a> APIs, TensorFlow.js allows users to use either Tensorflow.js models or converted models from TensorFlow or TFLite, retrain the given models, and run on the web.<sup id="cite_ref-:1_45-1" class="reference"><a href="#cite_note-:1-45"><span class="cite-bracket">[</span>45<span class="cite-bracket">]</span></a></sup><sup id="cite_ref-63" class="reference"><a href="#cite_note-63"><span class="cite-bracket">[</span>63<span class="cite-bracket">]</span></a></sup>

</p>

<div class="mw-heading mw-heading3"><h3 id="LiteRT">LiteRT</h3></div>

<p>LiteRT, formerly known as TensorFlow Lite,<sup id="cite_ref-64" class="reference"><a href="#cite_note-64"><span class="cite-bracket">[</span>64<span class="cite-bracket">]</span></a></sup> has APIs for mobile apps or embedded devices to generate and deploy TensorFlow models.<sup id="cite_ref-65" class="reference"><a href="#cite_note-65"><span class="cite-bracket">[</span>65<span class="cite-bracket">]</span></a></sup> These models are compressed and optimized in order to be more efficient and have a higher performance on smaller capacity devices.<sup id="cite_ref-:14_66-0" class="reference"><a href="#cite_note-:14-66"><span class="cite-bracket">[</span>66<span class="cite-bracket">]</span></a></sup>

</p><p>LiteRT uses <a href="FlatBuffers" title="FlatBuffers">FlatBuffers</a> as the data serialization format for network models, eschewing the <a href="Protocol_Buffers" title="Protocol Buffers">Protocol Buffers</a> format used by standard TensorFlow models.<sup id="cite_ref-:14_66-1" class="reference"><a href="#cite_note-:14-66"><span class="cite-bracket">[</span>66<span class="cite-bracket">]</span></a></sup>

</p>

<p>TensorFlow Extended (abbrev. TFX) provides numerous components to perform all the operations needed for end-to-end production.<sup id="cite_ref-:2_67-0" class="reference"><a href="#cite_note-:2-67"><span class="cite-bracket">[</span>67<span class="cite-bracket">]</span></a></sup> Components include loading, validating, and transforming data, tuning, training, and evaluating the machine learning model, and pushing the model itself into production.<sup id="cite_ref-:1_45-2" class="reference"><a href="#cite_note-:1-45"><span class="cite-bracket">[</span>45<span class="cite-bracket">]</span></a></sup><sup id="cite_ref-:2_67-1" class="reference"><a href="#cite_note-:2-67"><span class="cite-bracket">[</span>67<span class="cite-bracket">]</span></a></sup>

</p>

<div class="mw-heading mw-heading3"><h3 id="Integrations">Integrations</h3></div>

<div class="mw-heading mw-heading4"><h4 id="Numpy">Numpy</h4></div>

<p><a href="NumPy" title="NumPy">Numpy</a> is one of the most popular <a href="Python_(programming_language)" title="Python (programming language)">Python</a> data libraries, and TensorFlow offers integration and compatibility with its data structures.<sup id="cite_ref-:15_68-0" class="reference"><a href="#cite_note-:15-68"><span class="cite-bracket">[</span>68<span class="cite-bracket">]</span></a></sup> Numpy NDarrays, the library's native datatype, are automatically converted to TensorFlow Tensors in TF operations; the same is also true vice versa.<sup id="cite_ref-:15_68-1" class="reference"><a href="#cite_note-:15-68"><span class="cite-bracket">[</span>68<span class="cite-bracket">]</span></a></sup> This allows for the two libraries to work in unison without requiring the user to write explicit data conversions. Moreover, the integration extends to memory optimization by having TF Tensors share the underlying memory representations of Numpy NDarrays whenever possible.<sup id="cite_ref-:15_68-2" class="reference"><a href="#cite_note-:15-68"><span class="cite-bracket">[</span>68<span class="cite-bracket">]</span></a></sup>

</p>

<div class="mw-heading mw-heading3"><h3 id="Extensions">Extensions</h3></div>

<p>TensorFlow also offers a variety of <a href="Library_(computing)" title="Library (computing)">libraries</a> and <a href="Plug-in_(computing)" title="Plug-in (computing)">extensions</a> to advance and extend the models and methods used.<sup id="cite_ref-:33_69-0" class="reference"><a href="#cite_note-:33-69"><span class="cite-bracket">[</span>69<span class="cite-bracket">]</span></a></sup> For example, TensorFlow Recommenders and TensorFlow Graphics are <a href="Library_(computing)" title="Library (computing)">libraries</a> for their respective functional.<sup id="cite_ref-:43_70-0" class="reference"><a href="#cite_note-:43-70"><span class="cite-bracket">[</span>70<span class="cite-bracket">]</span></a></sup> Other add-ons, <a href="Library_(computing)" title="Library (computing)">libraries</a>, and <a href="Software_framework" title="Software framework">frameworks</a> include TensorFlow Model Optimization, TensorFlow Probability, TensorFlow Quantum, and TensorFlow Decision Forests.<sup id="cite_ref-:33_69-1" class="reference"><a href="#cite_note-:33-69"><span class="cite-bracket">[</span>69<span class="cite-bracket">]</span></a></sup><sup id="cite_ref-:43_70-1" class="reference"><a href="#cite_note-:43-70"><span class="cite-bracket">[</span>70<span class="cite-bracket">]</span></a></sup>

</p>

<div class="mw-heading mw-heading4"><h4 id="Google_Colab">Google Colab</h4></div>

<p>Google also released <a href="Google_Colab" title="Google Colab">Colaboratory</a>, a TensorFlow <a href="Jupyter_notebook" class="mw-redirect" title="Jupyter notebook">Jupyter notebook</a> environment that does not require any setup.<sup id="cite_ref-71" class="reference"><a href="#cite_note-71"><span class="cite-bracket">[</span>71<span class="cite-bracket">]</span></a></sup> It runs on Google Cloud and allows users free access to GPUs and the ability to store and share notebooks on <a href="Google_Drive" title="Google Drive">Google Drive</a>.<sup id="cite_ref-72" class="reference"><a href="#cite_note-72"><span class="cite-bracket">[</span>72<span class="cite-bracket">]</span></a></sup>

</p>

<div class="mw-heading mw-heading4"><h4 id="Google_JAX">Google JAX</h4></div>

<div role="note" class="hatnote navigation-not-searchable">Main article: <a href="Google_JAX" class="mw-redirect" title="Google JAX">Google JAX</a></div>

<p><a href="Google_JAX" class="mw-redirect" title="Google JAX">Google JAX</a> is a machine learning <a href="Software_framework" title="Software framework">framework</a> for transforming numerical functions.<sup id="cite_ref-:jax_73-0" class="reference"><a href="#cite_note-:jax-73"><span class="cite-bracket">[</span>73<span class="cite-bracket">]</span></a></sup><sup id="cite_ref-74" class="reference"><a href="#cite_note-74"><span class="cite-bracket">[</span>74<span class="cite-bracket">]</span></a></sup><sup id="cite_ref-75" class="reference"><a href="#cite_note-75"><span class="cite-bracket">[</span>75<span class="cite-bracket">]</span></a></sup> It is described as bringing together a modified version of <a rel="nofollow" class="external text" href="https://github.com/HIPS/autograd">autograd</a> (automatic obtaining of the gradient function through differentiation of a function) and TensorFlow's <a rel="nofollow" class="external text" href="https://www.tensorflow.org/xla">XLA</a> (Accelerated Linear Algebra). It is designed to follow the structure and workflow of <a href="NumPy" title="NumPy">NumPy</a> as closely as possible and works with TensorFlow as well as other frameworks such as <a href="PyTorch" title="PyTorch">PyTorch</a>. The primary functions of JAX are:<sup id="cite_ref-:jax_73-1" class="reference"><a href="#cite_note-:jax-73"><span class="cite-bracket">[</span>73<span class="cite-bracket">]</span></a></sup>

</p>

<ol><li>grad: automatic differentiation</li>

<li>jit: compilation</li>

<li>vmap: auto-vectorization</li>

<li>pmap: SPMD programming</li></ol>

<div class="mw-heading mw-heading2"><h2 id="Applications">Applications</h2></div>

<div class="mw-heading mw-heading3"><h3 id="Medical">Medical</h3></div>

<p><a href="GE_Healthcare" class="mw-redirect" title="GE Healthcare">GE Healthcare</a> used TensorFlow to increase the speed and accuracy of <a href="Magnetic_resonance_imaging" title="Magnetic resonance imaging">MRIs</a> in identifying specific body parts.<sup id="cite_ref-76" class="reference"><a href="#cite_note-76"><span class="cite-bracket">[</span>76<span class="cite-bracket">]</span></a></sup> Google used TensorFlow to create DermAssist, a free mobile application that allows users to take pictures of their skin and identify potential health complications.<sup id="cite_ref-:6_77-0" class="reference"><a href="#cite_note-:6-77"><span class="cite-bracket">[</span>77<span class="cite-bracket">]</span></a></sup> <a href="Sinovation_Ventures" title="Sinovation Ventures">Sinovation Ventures</a> used TensorFlow to identify and classify eye diseases from <a href="Optical_coherence_tomography" title="Optical coherence tomography">optical coherence tomography</a> (OCT) scans.<sup id="cite_ref-:6_77-1" class="reference"><a href="#cite_note-:6-77"><span class="cite-bracket">[</span>77<span class="cite-bracket">]</span></a></sup>

</p>

<div class="mw-heading mw-heading3"><h3 id="Social_media">Social media</h3></div>

<p><a href="Twitter" title="Twitter">Twitter</a> implemented TensorFlow to rank tweets by importance for a given user, and changed their platform to show tweets in order of this ranking.<sup id="cite_ref-:7_78-0" class="reference"><a href="#cite_note-:7-78"><span class="cite-bracket">[</span>78<span class="cite-bracket">]</span></a></sup> Previously, tweets were simply shown in reverse chronological order.<sup id="cite_ref-:7_78-1" class="reference"><a href="#cite_note-:7-78"><span class="cite-bracket">[</span>78<span class="cite-bracket">]</span></a></sup> The photo sharing app <a href="VSCO" title="VSCO">VSCO</a> used TensorFlow to help suggest custom filters for photos.<sup id="cite_ref-:6_77-2" class="reference"><a href="#cite_note-:6-77"><span class="cite-bracket">[</span>77<span class="cite-bracket">]</span></a></sup>

</p>

<div class="mw-heading mw-heading3"><h3 id="Search_Engine">Search Engine</h3></div>

<p><a href="Google" title="Google">Google</a> officially released <a href="RankBrain" title="RankBrain">RankBrain</a> on October 26, 2015, backed by TensorFlow.<sup id="cite_ref-79" class="reference"><a href="#cite_note-79"><span class="cite-bracket">[</span>79<span class="cite-bracket">]</span></a></sup>

</p>

<div class="mw-heading mw-heading3"><h3 id="Education">Education</h3></div>

<p>InSpace, a virtual learning platform, used TensorFlow to filter out toxic chat messages in classrooms.<sup id="cite_ref-80" class="reference"><a href="#cite_note-80"><span class="cite-bracket">[</span>80<span class="cite-bracket">]</span></a></sup> Liulishuo, an online English learning platform, utilized TensorFlow to create an adaptive curriculum for each student.<sup id="cite_ref-:8_81-0" class="reference"><a href="#cite_note-:8-81"><span class="cite-bracket">[</span>81<span class="cite-bracket">]</span></a></sup> TensorFlow was used to accurately assess a student's current abilities, and also helped decide the best future content to show based on those capabilities.<sup id="cite_ref-:8_81-1" class="reference"><a href="#cite_note-:8-81"><span class="cite-bracket">[</span>81<span class="cite-bracket">]</span></a></sup>

</p>

<div class="mw-heading mw-heading3"><h3 id="Retail">Retail</h3></div>

<p>The e-commerce platform <a href="Carousell_(company)" title="Carousell (company)">Carousell</a> used TensorFlow to provide personalized recommendations for customers.<sup id="cite_ref-:6_77-3" class="reference"><a href="#cite_note-:6-77"><span class="cite-bracket">[</span>77<span class="cite-bracket">]</span></a></sup> The cosmetics company ModiFace used TensorFlow to create an augmented reality experience for customers to test various shades of make-up on their face.<sup id="cite_ref-82" class="reference"><a href="#cite_note-82"><span class="cite-bracket">[</span>82<span class="cite-bracket">]</span></a></sup>

</p>

/* start https://en.wikipedia.org/ */

.mw-parser-output .tmulti .multiimageinner{display:flex;flex-direction:column}.mw-parser-output .tmulti .trow{display:flex;flex-direction:row;clear:left;flex-wrap:wrap;width:100%;box-sizing:border-box}.mw-parser-output .tmulti .tsingle{margin:1px;float:left}.mw-parser-output .tmulti .theader{clear:both;font-weight:bold;text-align:center;align-self:center;background-color:transparent;width:100%}.mw-parser-output .tmulti .thumbcaption{background-color:transparent}.mw-parser-output .tmulti .text-align-left{text-align:left}.mw-parser-output .tmulti .text-align-right{text-align:right}.mw-parser-output .tmulti .text-align-center{text-align:center}@media all and (max-width:720px){.mw-parser-output .tmulti .thumbinner{width:100%!important;box-sizing:border-box;max-width:none!important;align-items:center}.mw-parser-output .tmulti .trow{justify-content:center}.mw-parser-output .tmulti .tsingle{float:none!important;max-width:100%!important;box-sizing:border-box;text-align:center}.mw-parser-output .tmulti .tsingle .thumbcaption{text-align:left}.mw-parser-output .tmulti .trow>.thumbcaption{text-align:center}}@media screen{html.skin-theme-clientpref-night .mw-parser-output .tmulti .multiimageinner span:not(.skin-invert-image):not(.skin-invert):not(.bg-transparent) img{background-color:white}}@media screen and (prefers-color-scheme:dark){html.skin-theme-clientpref-os .mw-parser-output .tmulti .multiimageinner span:not(.skin-invert-image):not(.skin-invert):not(.bg-transparent) img{background-color:white}}

/* end https://en.wikipedia.org/ */

</style><div class="thumb tmulti tright"><div class="thumbinner multiimageinner" style="width:308px;max-width:308px"><div class="trow"><div class="tsingle" style="width:152px;max-width:152px"><div class="thumbimage"><span typeof="mw:File"></span></div></div><div class="tsingle" style="width:152px;max-width:152px"><div class="thumbimage"><span typeof="mw:File"></span></div></div></div><div class="trow" style="display:flex"><div class="thumbcaption">2016 comparison of original photo (left) and with TensorFlow <i>neural style</i> applied (right)</div></div></div></div>

<div class="mw-heading mw-heading3"><h3 id="Research">Research</h3></div>

<p>TensorFlow is the foundation for the automated <a href="Image_captioning" class="mw-redirect" title="Image captioning">image-captioning</a> software <a href="DeepDream" title="DeepDream">DeepDream</a>.<sup id="cite_ref-Byrne_83-0" class="reference"><a href="#cite_note-Byrne-83"><span class="cite-bracket">[</span>83<span class="cite-bracket">]</span></a></sup>

</p>

/* start https://en.wikipedia.org/ */

.mw-parser-output .portalbox{padding:0;margin:0.5em 0;display:table;box-sizing:border-box;max-width:175px;list-style:none}.mw-parser-output .portalborder{border:1px solid var(--border-color-base,#a2a9b1);padding:0.1em;background:var(--background-color-neutral-subtle,#f8f9fa)}.mw-parser-output .portalbox-entry{display:table-row;font-size:85%;line-height:110%;height:1.9em;font-style:italic;font-weight:bold}.mw-parser-output .portalbox-image{display:table-cell;padding:0.2em;vertical-align:middle;text-align:center}.mw-parser-output .portalbox-link{display:table-cell;padding:0.2em 0.2em 0.2em 0.3em;vertical-align:middle}@media(min-width:720px){.mw-parser-output .portalleft{margin:0.5em 1em 0.5em 0}.mw-parser-output .portalright{clear:right;float:right;margin:0.5em 0 0.5em 1em}}

/* end https://en.wikipedia.org/ */

</style>

<ul><li><a href="Comparison_of_deep_learning_software" title="Comparison of deep learning software">Comparison of deep learning software</a></li>

<li><a href="Differentiable_programming" title="Differentiable programming">Differentiable programming</a></li>

<li><a href="Keras" title="Keras">Keras</a></li></ul>

<div class="mw-heading mw-heading2"><h2 id="References">References</h2></div>

/* start https://en.wikipedia.org/ */

.mw-parser-output .reflist{margin-bottom:0.5em;list-style-type:decimal}@media screen{.mw-parser-output .reflist{font-size:90%}}.mw-parser-output .reflist .references{font-size:100%;margin-bottom:0;list-style-type:inherit}.mw-parser-output .reflist-columns-2{column-width:30em}.mw-parser-output .reflist-columns-3{column-width:25em}.mw-parser-output .reflist-columns{margin-top:0.3em}.mw-parser-output .reflist-columns ol{margin-top:0}.mw-parser-output .reflist-columns li{page-break-inside:avoid;break-inside:avoid-column}.mw-parser-output .reflist-upper-alpha{list-style-type:upper-alpha}.mw-parser-output .reflist-upper-roman{list-style-type:upper-roman}.mw-parser-output .reflist-lower-alpha{list-style-type:lower-alpha}.mw-parser-output .reflist-lower-greek{list-style-type:lower-greek}.mw-parser-output .reflist-lower-roman{list-style-type:lower-roman}

/* end https://en.wikipedia.org/ */

</style><div class="reflist">

/* start https://en.wikipedia.org/ */

.mw-parser-output cite.citation{font-style:inherit;word-wrap:break-word}.mw-parser-output .citation q{quotes:"\"""\"""'""'"}.mw-parser-output .citation:target{background-color:rgba(0,127,255,0.133)}.mw-parser-output .id-lock-free.id-lock-free a{background:url("./mw/Lock-green.svg")right 0.1em center/9px no-repeat}.mw-parser-output .id-lock-limited.id-lock-limited a,.mw-parser-output .id-lock-registration.id-lock-registration a{background:url("./mw/Lock-gray-alt-2.svg")right 0.1em center/9px no-repeat}.mw-parser-output .id-lock-subscription.id-lock-subscription a{background:url("./mw/Lock-red-alt-2.svg")right 0.1em center/9px no-repeat}.mw-parser-output .cs1-ws-icon a{background:url("./mw/Wikisource-logo.svg")right 0.1em center/12px no-repeat}body:not(.skin-timeless):not(.skin-minerva) .mw-parser-output .id-lock-free a,body:not(.skin-timeless):not(.skin-minerva) .mw-parser-output .id-lock-limited a,body:not(.skin-timeless):not(.skin-minerva) .mw-parser-output .id-lock-registration a,body:not(.skin-timeless):not(.skin-minerva) .mw-parser-output .id-lock-subscription a,body:not(.skin-timeless):not(.skin-minerva) .mw-parser-output .cs1-ws-icon a{background-size:contain;padding:0 1em 0 0}.mw-parser-output .cs1-code{color:inherit;background:inherit;border:none;padding:inherit}.mw-parser-output .cs1-hidden-error{display:none;color:var(--color-error,#d33)}.mw-parser-output .cs1-visible-error{color:var(--color-error,#d33)}.mw-parser-output .cs1-maint{display:none;color:#085;margin-left:0.3em}.mw-parser-output .cs1-kern-left{padding-left:0.2em}.mw-parser-output .cs1-kern-right{padding-right:0.2em}.mw-parser-output .citation .mw-selflink{font-weight:inherit}@media screen{.mw-parser-output .cs1-format{font-size:95%}html.skin-theme-clientpref-night .mw-parser-output .cs1-maint{color:#18911f}}@media screen and (prefers-color-scheme:dark){html.skin-theme-clientpref-os .mw-parser-output .cs1-maint{color:#18911f}}

/* end https://en.wikipedia.org/ */

</style><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://tensorflow.org/about">"Credits"</a>. <i>TensorFlow.org</i>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20151117032147/https://tensorflow.org/about">Archived</a> from the original on November 17, 2015<span class="reference-accessdate">. Retrieved <span class="nowrap">November 10,</span> 2015</span>.</cite></span>

</li>

<li id="cite_note-js-2"><span class="mw-cite-backlink"><b><a href="#cite_ref-js_2-0">^</a></b></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://js.tensorflow.org/faq/">"TensorFlow.js"</a>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20180506083002/https://js.tensorflow.org/faq/">Archived</a> from the original on May 6, 2018<span class="reference-accessdate">. Retrieved <span class="nowrap">June 28,</span> 2018</span>.</cite></span>

</li>

<li id="cite_note-3"><span class="mw-cite-backlink"><b><a href="#cite_ref-3">^</a></b></span> <span class="reference-text"><cite id="CITEREFAbadiBarhamChenChen2016" class="citation conference cs1">Abadi, Martín; Barham, Paul; Chen, Jianmin; Chen, Zhifeng; Davis, Andy; Dean, Jeffrey; Devin, Matthieu; Ghemawat, Sanjay; Irving, Geoffrey; Isard, Michael; Kudlur, Manjunath; Levenberg, Josh; Monga, Rajat; Moore, Sherry; Murray, Derek G.; Steiner, Benoit; Tucker, Paul; Vasudevan, Vijay; Warden, Pete; Wicke, Martin; Yu, Yuan; Zheng, Xiaoqiang (2016). <a rel="nofollow" class="external text" href="https://www.usenix.org/system/files/conference/osdi16/osdi16-abadi.pdf"><i>TensorFlow: A System for Large-Scale Machine Learning</i></a> <span class="cs1-format">(PDF)</span>. Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI ’16). <a href="ArXiv_(identifier)" class="mw-redirect" title="ArXiv (identifier)">arXiv</a>:<span class="id-lock-free" title="Freely accessible"><a rel="nofollow" class="external text" href="https://arxiv.org/abs/1605.08695">1605.08695</a></span>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20201212042511/https://www.usenix.org/system/files/conference/osdi16/osdi16-abadi.pdf">Archived</a> <span class="cs1-format">(PDF)</span> from the original on December 12, 2020<span class="reference-accessdate">. Retrieved <span class="nowrap">October 26,</span> 2020</span>.</cite></span>

</li>

<li id="cite_note-YoutubeClip-4"><span class="mw-cite-backlink"><b><a href="#cite_ref-YoutubeClip_4-0">^</a></b></span> <span class="reference-text"><cite id="CITEREFVideo_clip_by_Google_about_TensorFlow2015" class="citation audio-visual cs1"><a rel="nofollow" class="external text" href="https://www.youtube.com/watch?v=oZikw5k_2FM"><i>TensorFlow: Open source machine learning</i></a>. Google. 2015. <a rel="nofollow" class="external text" href="https://ghostarchive.org/varchive/youtube/20211111/oZikw5k_2FM">Archived</a> from the original on November 11, 2021.</cite> "It is machine learning software being used for various kinds of perceptual and language understanding tasks" – Jeffrey Dean, minute 0:47 / 2:17 from YouTube clip</span>

</li>

<li id="cite_note-5"><span class="mw-cite-backlink"><b><a href="#cite_ref-5">^</a></b></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://github.com/cncf/velocity">"Top 30 Open Source Projects"</a>. <i>Open Source Project Velocity by CNCF</i>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20230903024925/https://github.com/cncf/velocity">Archived</a> from the original on September 3, 2023<span class="reference-accessdate">. Retrieved <span class="nowrap">October 12,</span> 2023</span>.</cite></span>

</li>

<li id="cite_note-6"><span class="mw-cite-backlink"><b><a href="#cite_ref-6">^</a></b></span> <span class="reference-text"><a href="#CITEREFVideo_clip_by_Google_about_TensorFlow2015">Video clip by Google about TensorFlow 2015</a> at minute 0:15/2:17</span>

</li>

<li id="cite_note-7"><span class="mw-cite-backlink"><b><a href="#cite_ref-7">^</a></b></span> <span class="reference-text"><a href="#CITEREFVideo_clip_by_Google_about_TensorFlow2015">Video clip by Google about TensorFlow 2015</a> at minute 0:26/2:17</span>

</li>

</li>

<li id="cite_note-Metz-Nov9-9"><span class="mw-cite-backlink"><b><a href="#cite_ref-Metz-Nov9_9-0">^</a></b></span> <span class="reference-text"><cite id="CITEREFMetz2015" class="citation web cs1">Metz, Cade (November 9, 2015). <a rel="nofollow" class="external text" href="https://www.wired.com/2015/11/google-open-sources-its-artificial-intelligence-engine/">"Google Just Open Sourced TensorFlow, Its Artificial Intelligence Engine"</a>. <i><a href="Wired_(website)" class="mw-redirect" title="Wired (website)">Wired</a></i>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20151109142618/https://www.wired.com/2015/11/google-open-sources-its-artificial-intelligence-engine/">Archived</a> from the original on November 9, 2015<span class="reference-accessdate">. Retrieved <span class="nowrap">November 10,</span> 2015</span>.</cite></span>

</li>

<li id="cite_note-:12-10"><span class="mw-cite-backlink">^ <a href="#cite_ref-:12_10-0"><sup><i><b>a</b></i></sup></a> <a href="#cite_ref-:12_10-1"><sup><i><b>b</b></i></sup></a></span> <span class="reference-text"><cite id="CITEREFTensorFlow2019" class="citation web cs1">TensorFlow (September 30, 2019). <a rel="nofollow" class="external text" href="https://medium.com/tensorflow/tensorflow-2-0-is-now-available-57d706c2a9ab">"TensorFlow 2.0 is now available!"</a>. <i>Medium</i>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20191007214705/https://medium.com/tensorflow/tensorflow-2-0-is-now-available-57d706c2a9ab">Archived</a> from the original on October 7, 2019<span class="reference-accessdate">. Retrieved <span class="nowrap">November 24,</span> 2019</span>.</cite></span>

</li>

<li id="cite_note-:13-11"><span class="mw-cite-backlink">^ <a href="#cite_ref-:13_11-0"><sup><i><b>a</b></i></sup></a> <a href="#cite_ref-:13_11-1"><sup><i><b>b</b></i></sup></a></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://www.tensorflow.org/api_docs/">"API Documentation"</a>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20151116154736/https://www.tensorflow.org/api_docs/">Archived</a> from the original on November 16, 2015<span class="reference-accessdate">. Retrieved <span class="nowrap">June 27,</span> 2018</span>.</cite>,</span>

</li>

<li id="cite_note-whitepaper2015-12"><span class="mw-cite-backlink"><b><a href="#cite_ref-whitepaper2015_12-0">^</a></b></span> <span class="reference-text"><cite id="CITEREFDean_et_al2015" class="citation web cs1"><a href="Jeff_Dean_(computer_scientist)" class="mw-redirect" title="Jeff Dean (computer scientist)">Dean, Jeff</a>; Monga, Rajat; et al. (November 9, 2015). <a rel="nofollow" class="external text" href="http://download.tensorflow.org/paper/whitepaper2015.pdf">"TensorFlow: Large-scale machine learning on heterogeneous systems"</a> <span class="cs1-format">(PDF)</span>. <i>TensorFlow.org</i>. Google Research. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20151120004649/http://download.tensorflow.org/paper/whitepaper2015.pdf">Archived</a> <span class="cs1-format">(PDF)</span> from the original on November 20, 2015<span class="reference-accessdate">. Retrieved <span class="nowrap">November 10,</span> 2015</span>.</cite></span>

</li>

<li id="cite_note-Perez-13"><span class="mw-cite-backlink"><b><a href="#cite_ref-Perez_13-0">^</a></b></span> <span class="reference-text"><cite id="CITEREFPerez2015" class="citation web cs1">Perez, Sarah (November 9, 2015). <a rel="nofollow" class="external text" href="https://techcrunch.com/2015/11/09/google-open-sources-the-machine-learning-tech-behind-google-photos-search-smart-reply-and-more/">"Google Open-Sources The Machine Learning Tech Behind Google Photos Search, Smart Reply And More"</a>. <i>TechCrunch</i>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20151109150138/https://techcrunch.com/2015/11/09/google-open-sources-the-machine-learning-tech-behind-google-photos-search-smart-reply-and-more/">Archived</a> from the original on November 9, 2015<span class="reference-accessdate">. Retrieved <span class="nowrap">November 11,</span> 2015</span>.</cite></span>

</li>

<li id="cite_note-Oremus-14"><span class="mw-cite-backlink"><b><a href="#cite_ref-Oremus_14-0">^</a></b></span> <span class="reference-text"><cite id="CITEREFOremus2015" class="citation web cs1">Oremus, Will (November 9, 2015). <a rel="nofollow" class="external text" href="https://www.slate.com/blogs/future_tense/2015/11/09/google_s_tensorflow_is_open_source_and_it_s_about_to_be_a_huge_huge_deal.html">"What Is TensorFlow, and Why Is Google So Excited About It?"</a>. <i>Slate</i>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20151110021146/https://www.slate.com/blogs/future_tense/2015/11/09/google_s_tensorflow_is_open_source_and_it_s_about_to_be_a_huge_huge_deal.html">Archived</a> from the original on November 10, 2015<span class="reference-accessdate">. Retrieved <span class="nowrap">November 11,</span> 2015</span>.</cite></span>

</li>

<li id="cite_note-Ward-Bailey-15"><span class="mw-cite-backlink"><b><a href="#cite_ref-Ward-Bailey_15-0">^</a></b></span> <span class="reference-text"><cite id="CITEREFWard-Bailey2015" class="citation web cs1">Ward-Bailey, Jeff (November 25, 2015). <a rel="nofollow" class="external text" href="https://www.csmonitor.com/Technology/2015/0914/Google-chairman-We-re-making-real-progress-on-artificial-intelligence">"Google chairman: We're making 'real progress' on artificial intelligence"</a>. <i>CSMonitor</i>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20150916223243/https://www.csmonitor.com/Technology/2015/0914/Google-chairman-We-re-making-real-progress-on-artificial-intelligence">Archived</a> from the original on September 16, 2015<span class="reference-accessdate">. Retrieved <span class="nowrap">November 25,</span> 2015</span>.</cite></span>

</li>

<li id="cite_note-16"><span class="mw-cite-backlink"><b><a href="#cite_ref-16">^</a></b></span> <span class="reference-text"><cite id="CITEREFTensorFlow_Developers2022" class="citation journal cs1">TensorFlow Developers (2022). <a rel="nofollow" class="external text" href="https://github.com/tensorflow/tensorflow/blob/07bb8ea2379bd459832b23951fb20ec47f3fdbd4/RELEASE.md">"Tensorflow Release 1.0.0"</a>. <i><a href="GitHub" title="GitHub">GitHub</a></i>. <a href="Doi_(identifier)" class="mw-redirect" title="Doi (identifier)">doi</a>:<a rel="nofollow" class="external text" href="https://doi.org/10.5281%2Fzenodo.4724125">10.5281/zenodo.4724125</a>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20210227171533/https://github.com/tensorflow/tensorflow/blob/07bb8ea2379bd459832b23951fb20ec47f3fdbd4/RELEASE.md">Archived</a> from the original on February 27, 2021<span class="reference-accessdate">. Retrieved <span class="nowrap">July 24,</span> 2017</span>.</cite></span>

</li>

<li id="cite_note-Metz-Nov10-17"><span class="mw-cite-backlink"><b><a href="#cite_ref-Metz-Nov10_17-0">^</a></b></span> <span class="reference-text"><cite id="CITEREFMetz2015" class="citation news cs1">Metz, Cade (November 10, 2015). <a rel="nofollow" class="external text" href="https://www.wired.com/2015/11/googles-open-source-ai-tensorflow-signals-fast-changing-hardware-world/">"TensorFlow, Google's Open Source AI, Points to a Fast-Changing Hardware World"</a>. <i>Wired</i>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20151111163641/http://www.wired.com/2015/11/googles-open-source-ai-tensorflow-signals-fast-changing-hardware-world/">Archived</a> from the original on November 11, 2015<span class="reference-accessdate">. Retrieved <span class="nowrap">November 11,</span> 2015</span>.</cite></span>

</li>

<li id="cite_note-18"><span class="mw-cite-backlink"><b><a href="#cite_ref-18">^</a></b></span> <span class="reference-text"><cite id="CITEREFKudale2020" class="citation web cs1">Kudale, Aniket Eknath (June 8, 2020). <a rel="nofollow" class="external text" href="https://www.opensourceforu.com/2020/06/building-a-facial-expression-recognition-app-using-tensorflow-js/">"Building a Facial Expression Recognition App Using TensorFlow.js"</a>. <i>Open Source For U</i>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20241011214722/https://www.opensourceforu.com/2020/06/building-a-facial-expression-recognition-app-using-tensorflow-js/">Archived</a> from the original on October 11, 2024<span class="reference-accessdate">. Retrieved <span class="nowrap">April 19,</span> 2025</span>.</cite></span>

</li>

<li id="cite_note-19"><span class="mw-cite-backlink"><b><a href="#cite_ref-19">^</a></b></span> <span class="reference-text"><cite id="CITEREFMSV2021" class="citation web cs1">MSV, Janakiram (February 24, 2021). <a rel="nofollow" class="external text" href="https://thenewstack.io/the-ultimate-guide-to-machine-learning-frameworks/">"The Ultimate Guide to Machine Learning Frameworks"</a>. <i>The New Stack</i>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20241224100937/https://thenewstack.io/the-ultimate-guide-to-machine-learning-frameworks/">Archived</a> from the original on December 24, 2024<span class="reference-accessdate">. Retrieved <span class="nowrap">April 19,</span> 2025</span>.</cite></span>

</li>

<li id="cite_note-20"><span class="mw-cite-backlink"><b><a href="#cite_ref-20">^</a></b></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://www.tensorflow.org/guide/tensor">"Introduction to tensors"</a>. tensorflow.org. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20240526120806/https://www.tensorflow.org/guide/tensor">Archived</a> from the original on May 26, 2024<span class="reference-accessdate">. Retrieved <span class="nowrap">March 3,</span> 2024</span>.</cite></span>

</li>

<li id="cite_note-1500repo's-21"><span class="mw-cite-backlink"><b><a href="#cite_ref-1500repo's_21-0">^</a></b></span> <span class="reference-text"><a rel="nofollow" class="external text" href="https://www.youtube.com/watch?v=Rnm83GqgqPE">Machine Learning: Google I/O 2016 Minute 07:30/44:44 </a>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20161221095258/https://www.youtube.com/watch?v=Rnm83GqgqPE">Archived</a> December 21, 2016, at the <a href="Wayback_Machine" title="Wayback Machine">Wayback Machine</a>. Retrieved June 5, 2016.</span>

</li>

<li id="cite_note-22"><span class="mw-cite-backlink"><b><a href="#cite_ref-22">^</a></b></span> <span class="reference-text"><cite id="CITEREFTensorFlow2018" class="citation web cs1">TensorFlow (March 30, 2018). <a rel="nofollow" class="external text" href="https://medium.com/tensorflow/introducing-tensorflow-js-machine-learning-in-javascript-bf3eab376db">"Introducing TensorFlow.js: Machine Learning in Javascript"</a>. <i>Medium</i>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20180330180144/https://medium.com/tensorflow/introducing-tensorflow-js-machine-learning-in-javascript-bf3eab376db">Archived</a> from the original on March 30, 2018<span class="reference-accessdate">. Retrieved <span class="nowrap">May 24,</span> 2019</span>.</cite></span>

</li>

<li id="cite_note-23"><span class="mw-cite-backlink"><b><a href="#cite_ref-23">^</a></b></span> <span class="reference-text"><cite id="CITEREFTensorFlow2019" class="citation web cs1">TensorFlow (January 14, 2019). <a rel="nofollow" class="external text" href="https://medium.com/tensorflow/whats-coming-in-tensorflow-2-0-d3663832e9b8">"What's coming in TensorFlow 2.0"</a>. <i>Medium</i>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20190114181937/https://medium.com/tensorflow/whats-coming-in-tensorflow-2-0-d3663832e9b8">Archived</a> from the original on January 14, 2019<span class="reference-accessdate">. Retrieved <span class="nowrap">May 24,</span> 2019</span>.</cite></span>

</li>

<li id="cite_note-24"><span class="mw-cite-backlink"><b><a href="#cite_ref-24">^</a></b></span> <span class="reference-text"><cite id="CITEREFTensorFlow2019" class="citation web cs1">TensorFlow (May 9, 2019). <a rel="nofollow" class="external text" href="https://medium.com/tensorflow/introducing-tensorflow-graphics-computer-graphics-meets-deep-learning-c8e3877b7668">"Introducing TensorFlow Graphics: Computer Graphics Meets Deep Learning"</a>. <i>Medium</i>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20190509204620/https://medium.com/tensorflow/introducing-tensorflow-graphics-computer-graphics-meets-deep-learning-c8e3877b7668">Archived</a> from the original on May 9, 2019<span class="reference-accessdate">. Retrieved <span class="nowrap">May 24,</span> 2019</span>.</cite></span>

</li>

<li id="cite_note-25"><span class="mw-cite-backlink"><b><a href="#cite_ref-25">^</a></b></span> <span class="reference-text"><cite id="CITEREFJouppi" class="citation web cs1"><a href="Norman_Jouppi" title="Norman Jouppi">Jouppi, Norm</a>. <a rel="nofollow" class="external text" href="https://cloudplatform.googleblog.com/2016/05/Google-supercharges-machine-learning-tasks-with-custom-chip.html">"Google supercharges machine learning tasks with TPU custom chip"</a>. <i>Google Cloud Platform Blog</i>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20160518201516/https://cloudplatform.googleblog.com/2016/05/Google-supercharges-machine-learning-tasks-with-custom-chip.html">Archived</a> from the original on May 18, 2016<span class="reference-accessdate">. Retrieved <span class="nowrap">May 19,</span> 2016</span>.</cite></span>

</li>

<li id="cite_note-26"><span class="mw-cite-backlink"><b><a href="#cite_ref-26">^</a></b></span> <span class="reference-text"><cite class="citation news cs1"><a rel="nofollow" class="external text" href="https://www.blog.google/topics/google-cloud/google-cloud-offer-tpus-machine-learning/">"Build and train machine learning models on our new Google Cloud TPUs"</a>. <i>Google</i>. May 17, 2017. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20170517182035/https://blog.google/topics/google-cloud/google-cloud-offer-tpus-machine-learning/">Archived</a> from the original on May 17, 2017<span class="reference-accessdate">. Retrieved <span class="nowrap">May 18,</span> 2017</span>.</cite></span>

</li>

<li id="cite_note-27"><span class="mw-cite-backlink"><b><a href="#cite_ref-27">^</a></b></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://cloud.google.com/tpu/">"Cloud TPU"</a>. <i>Google Cloud</i>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20170517174135/https://cloud.google.com/tpu/">Archived</a> from the original on May 17, 2017<span class="reference-accessdate">. Retrieved <span class="nowrap">May 24,</span> 2019</span>.</cite></span>

</li>

<li id="cite_note-28"><span class="mw-cite-backlink"><b><a href="#cite_ref-28">^</a></b></span> <span class="reference-text"><cite class="citation news cs1"><a rel="nofollow" class="external text" href="https://cloudplatform.googleblog.com/2018/02/Cloud-TPU-machine-learning-accelerators-now-available-in-beta.html">"Cloud TPU machine learning accelerators now available in beta"</a>. <i>Google Cloud Platform Blog</i>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20180212141508/https://cloudplatform.googleblog.com/2018/02/Cloud-TPU-machine-learning-accelerators-now-available-in-beta.html">Archived</a> from the original on February 12, 2018<span class="reference-accessdate">. Retrieved <span class="nowrap">February 12,</span> 2018</span>.</cite></span>

</li>

<li id="cite_note-29"><span class="mw-cite-backlink"><b><a href="#cite_ref-29">^</a></b></span> <span class="reference-text"><cite id="CITEREFKundu2018" class="citation web cs1">Kundu, Kishalaya (July 26, 2018). <a rel="nofollow" class="external text" href="https://beebom.com/google-announces-edge-tpu-cloud-iot-edge-at-cloud-next-2018/">"Google Announces Edge TPU, Cloud IoT Edge at Cloud Next 2018"</a>. <i>Beebom</i>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20240526120854/https://beebom.com/google-announces-edge-tpu-cloud-iot-edge-at-cloud-next-2018/">Archived</a> from the original on May 26, 2024<span class="reference-accessdate">. Retrieved <span class="nowrap">February 2,</span> 2019</span>.</cite></span>

</li>

<li id="cite_note-30"><span class="mw-cite-backlink"><b><a href="#cite_ref-30">^</a></b></span> <span class="reference-text"><cite id="CITEREFVincent2017" class="citation web cs1">Vincent, James (May 17, 2017). <a rel="nofollow" class="external text" href="https://www.theverge.com/2017/5/17/15645908/google-ai-tensorflowlite-machine-learning-announcement-io-2017">"Google's new machine learning framework is going to put more AI on your phone"</a>. <i>The Verge</i>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20170517233339/https://www.theverge.com/2017/5/17/15645908/google-ai-tensorflowlite-machine-learning-announcement-io-2017">Archived</a> from the original on May 17, 2017<span class="reference-accessdate">. Retrieved <span class="nowrap">May 19,</span> 2017</span>.</cite></span>

</li>

<li id="cite_note-31"><span class="mw-cite-backlink"><b><a href="#cite_ref-31">^</a></b></span> <span class="reference-text"><cite id="CITEREFTensorFlow2019" class="citation web cs1">TensorFlow (January 16, 2019). <a rel="nofollow" class="external text" href="https://medium.com/tensorflow/tensorflow-lite-now-faster-with-mobile-gpus-developer-preview-e15797e6dee7">"TensorFlow Lite Now Faster with Mobile GPUs (Developer Preview)"</a>. <i>Medium</i>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20190116183459/https://medium.com/tensorflow/tensorflow-lite-now-faster-with-mobile-gpus-developer-preview-e15797e6dee7">Archived</a> from the original on January 16, 2019<span class="reference-accessdate">. Retrieved <span class="nowrap">May 24,</span> 2019</span>.</cite></span>

</li>

<li id="cite_note-32"><span class="mw-cite-backlink"><b><a href="#cite_ref-32">^</a></b></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://os.mbed.com/blog/entry/uTensor-and-Tensor-Flow-Announcement/">"uTensor and Tensor Flow Announcement | Mbed"</a>. <i>os.mbed.com</i>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20190509195115/https://os.mbed.com/blog/entry/uTensor-and-Tensor-Flow-Announcement/">Archived</a> from the original on May 9, 2019<span class="reference-accessdate">. Retrieved <span class="nowrap">May 24,</span> 2019</span>.</cite></span>

</li>

<li id="cite_note-:9-33"><span class="mw-cite-backlink">^ <a href="#cite_ref-:9_33-0"><sup><i><b>a</b></i></sup></a> <a href="#cite_ref-:9_33-1"><sup><i><b>b</b></i></sup></a></span> <span class="reference-text"><cite id="CITEREFHe2019" class="citation web cs1">He, Horace (October 10, 2019). <a rel="nofollow" class="external text" href="https://thegradient.pub/state-of-ml-frameworks-2019-pytorch-dominates-research-tensorflow-dominates-industry/">"The State of Machine Learning Frameworks in 2019"</a>. The Gradient. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20191010161542/https://thegradient.pub/state-of-ml-frameworks-2019-pytorch-dominates-research-tensorflow-dominates-industry/">Archived</a> from the original on October 10, 2019<span class="reference-accessdate">. Retrieved <span class="nowrap">May 22,</span> 2020</span>.</cite></span>

</li>

<li id="cite_note-“introduction”-34"><span class="mw-cite-backlink">^ <a href="#cite_ref-“introduction”_34-0"><sup><i><b>a</b></i></sup></a> <a href="#cite_ref-“introduction”_34-1"><sup><i><b>b</b></i></sup></a></span> <span class="reference-text"><cite id="CITEREFCiaramellaCiaramella2024" class="citation book cs1"><a href="Alberto_Ciaramella" title="Alberto Ciaramella">Ciaramella, Alberto</a>; Ciaramella, Marco (July 2024). <i>Introduction to Artificial Intelligence: from data analysis to generative AI</i>. Intellisemantic Editions. <a href="ISBN_(identifier)" class="mw-redirect" title="ISBN (identifier)">ISBN</a> <bdi>9788894787603</bdi>.</cite></span>

</li>

<li id="cite_note-:0-35"><span class="mw-cite-backlink">^ <a href="#cite_ref-:0_35-0"><sup><i><b>a</b></i></sup></a> <a href="#cite_ref-:0_35-1"><sup><i><b>b</b></i></sup></a></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://www.tensorflow.org/guide/autodiff">"Introduction to gradients and automatic differentiation"</a>. <i>TensorFlow</i>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20211028054417/https://www.tensorflow.org/guide/autodiff">Archived</a> from the original on October 28, 2021<span class="reference-accessdate">. Retrieved <span class="nowrap">November 4,</span> 2021</span>.</cite></span>

</li>

<li id="cite_note-:3-36"><span class="mw-cite-backlink">^ <a href="#cite_ref-:3_36-0"><sup><i><b>a</b></i></sup></a> <a href="#cite_ref-:3_36-1"><sup><i><b>b</b></i></sup></a> <a href="#cite_ref-:3_36-2"><sup><i><b>c</b></i></sup></a></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://www.tensorflow.org/guide/eager">"Eager execution | TensorFlow Core"</a>. <i>TensorFlow</i>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20211104011333/https://www.tensorflow.org/guide/eager">Archived</a> from the original on November 4, 2021<span class="reference-accessdate">. Retrieved <span class="nowrap">November 4,</span> 2021</span>.</cite></span>

</li>

<li id="cite_note-:4-37"><span class="mw-cite-backlink">^ <a href="#cite_ref-:4_37-0"><sup><i><b>a</b></i></sup></a> <a href="#cite_ref-:4_37-1"><sup><i><b>b</b></i></sup></a></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://www.tensorflow.org/api_docs/python/tf/distribute">"Module: tf.distribute | TensorFlow Core v2.6.1"</a>. <i>TensorFlow</i>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20240526120808/https://www.tensorflow.org/api_docs/python/tf/distribute">Archived</a> from the original on May 26, 2024<span class="reference-accessdate">. Retrieved <span class="nowrap">November 4,</span> 2021</span>.</cite></span>

</li>

<li id="cite_note-38"><span class="mw-cite-backlink"><b><a href="#cite_ref-38">^</a></b></span> <span class="reference-text"><cite id="CITEREFSigeru.2014" class="citation book cs1">Sigeru., Omatu (2014). <a rel="nofollow" class="external text" href="http://worldcat.org/oclc/980886715"><i>Distributed Computing and Artificial Intelligence, 11th International Conference</i></a>. Springer International Publishing. <a href="ISBN_(identifier)" class="mw-redirect" title="ISBN (identifier)">ISBN</a> <bdi>978-3-319-07593-8</bdi>. <a href="OCLC_(identifier)" class="mw-redirect" title="OCLC (identifier)">OCLC</a> <a rel="nofollow" class="external text" href="https://search.worldcat.org/oclc/980886715">980886715</a>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20240526120810/https://search.worldcat.org/title/980886715">Archived</a> from the original on May 26, 2024<span class="reference-accessdate">. Retrieved <span class="nowrap">November 4,</span> 2021</span>.</cite></span>

</li>

<li id="cite_note-:5-39"><span class="mw-cite-backlink">^ <a href="#cite_ref-:5_39-0"><sup><i><b>a</b></i></sup></a> <a href="#cite_ref-:5_39-1"><sup><i><b>b</b></i></sup></a></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://www.tensorflow.org/api_docs/python/tf/losses">"Module: tf.losses | TensorFlow Core v2.6.1"</a>. <i>TensorFlow</i>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20211027133546/https://www.tensorflow.org/api_docs/python/tf/losses">Archived</a> from the original on October 27, 2021<span class="reference-accessdate">. Retrieved <span class="nowrap">November 4,</span> 2021</span>.</cite></span>

</li>

<li id="cite_note-40"><span class="mw-cite-backlink"><b><a href="#cite_ref-40">^</a></b></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://www.tensorflow.org/api_docs/python/tf/metrics">"Module: tf.metrics | TensorFlow Core v2.6.1"</a>. <i>TensorFlow</i>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20211104011333/https://www.tensorflow.org/api_docs/python/tf/metrics">Archived</a> from the original on November 4, 2021<span class="reference-accessdate">. Retrieved <span class="nowrap">November 4,</span> 2021</span>.</cite></span>

</li>

<li id="cite_note-:10-41"><span class="mw-cite-backlink">^ <a href="#cite_ref-:10_41-0"><sup><i><b>a</b></i></sup></a> <a href="#cite_ref-:10_41-1"><sup><i><b>b</b></i></sup></a></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://www.tensorflow.org/api_docs/python/tf/nn">"Module: tf.nn | TensorFlow Core v2.7.0"</a>. <i>TensorFlow</i>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20240526120809/https://www.tensorflow.org/api_docs/python/tf/nn">Archived</a> from the original on May 26, 2024<span class="reference-accessdate">. Retrieved <span class="nowrap">November 6,</span> 2021</span>.</cite></span>

</li>

<li id="cite_note-:11-42"><span class="mw-cite-backlink"><b><a href="#cite_ref-:11_42-0">^</a></b></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://www.tensorflow.org/api_docs/python/tf/optimizers">"Module: tf.optimizers | TensorFlow Core v2.7.0"</a>. <i>TensorFlow</i>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20211030152658/https://www.tensorflow.org/api_docs/python/tf/optimizers">Archived</a> from the original on October 30, 2021<span class="reference-accessdate">. Retrieved <span class="nowrap">November 6,</span> 2021</span>.</cite></span>

</li>

<li id="cite_note-43"><span class="mw-cite-backlink"><b><a href="#cite_ref-43">^</a></b></span> <span class="reference-text"><cite id="CITEREFDogoAfolabiNwuluTwala2018" class="citation book cs1">Dogo, E. M.; Afolabi, O. J.; Nwulu, N. I.; Twala, B.; Aigbavboa, C. O. (December 2018). <a rel="nofollow" class="external text" href="https://ieeexplore.ieee.org/document/8769211">"A Comparative Analysis of Gradient Descent-Based Optimization Algorithms on Convolutional Neural Networks"</a>. <i>2018 International Conference on Computational Techniques, Electronics and Mechanical Systems (CTEMS)</i>. pp. <span class="nowrap">92–</span>99. <a href="Doi_(identifier)" class="mw-redirect" title="Doi (identifier)">doi</a>:<a rel="nofollow" class="external text" href="https://doi.org/10.1109%2FCTEMS.2018.8769211">10.1109/CTEMS.2018.8769211</a>. <a href="ISBN_(identifier)" class="mw-redirect" title="ISBN (identifier)">ISBN</a> <bdi>978-1-5386-7709-4</bdi>. <a href="S2CID_(identifier)" class="mw-redirect" title="S2CID (identifier)">S2CID</a> <a rel="nofollow" class="external text" href="https://api.semanticscholar.org/CorpusID:198931032">198931032</a>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20240526120806/https://ieeexplore.ieee.org/document/8769211">Archived</a> from the original on May 26, 2024<span class="reference-accessdate">. Retrieved <span class="nowrap">July 25,</span> 2023</span>.</cite></span>

</li>

<li id="cite_note-44"><span class="mw-cite-backlink"><b><a href="#cite_ref-44">^</a></b></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://www.tensorflow.org/overview">"TensorFlow Core | Machine Learning for Beginners and Experts"</a>. <i>TensorFlow</i>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20230120082541/https://www.tensorflow.org/overview">Archived</a> from the original on January 20, 2023<span class="reference-accessdate">. Retrieved <span class="nowrap">November 4,</span> 2021</span>.</cite></span>

</li>

<li id="cite_note-:1-45"><span class="mw-cite-backlink">^ <a href="#cite_ref-:1_45-0"><sup><i><b>a</b></i></sup></a> <a href="#cite_ref-:1_45-1"><sup><i><b>b</b></i></sup></a> <a href="#cite_ref-:1_45-2"><sup><i><b>c</b></i></sup></a></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://www.tensorflow.org/learn">"Introduction to TensorFlow"</a>. <i>TensorFlow</i>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20230120082541/https://www.tensorflow.org/learn">Archived</a> from the original on January 20, 2023<span class="reference-accessdate">. Retrieved <span class="nowrap">October 28,</span> 2021</span>.</cite></span>

</li>

<li id="cite_note-46"><span class="mw-cite-backlink"><b><a href="#cite_ref-46">^</a></b></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://www.tensorflow.org/api_docs/python/tf/all_symbols">"All symbols in TensorFlow 2 | TensorFlow Core v2.7.0"</a>. <i>TensorFlow</i>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20211106055527/https://www.tensorflow.org/api_docs/python/tf/all_symbols">Archived</a> from the original on November 6, 2021<span class="reference-accessdate">. Retrieved <span class="nowrap">November 6,</span> 2021</span>.</cite></span>

</li>

<li id="cite_note-47"><span class="mw-cite-backlink"><b><a href="#cite_ref-47">^</a></b></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://js.tensorflow.org/">"TensorFlow.js"</a>. <i>js.tensorflow.org</i>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20240526120808/https://www.tensorflow.org/js">Archived</a> from the original on May 26, 2024<span class="reference-accessdate">. Retrieved <span class="nowrap">November 6,</span> 2021</span>.</cite></span>

</li>

<li id="cite_note-48"><span class="mw-cite-backlink"><b><a href="#cite_ref-48">^</a></b></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://www.tensorflow.org/api_docs/cc">"TensorFlow C++ API Reference | TensorFlow Core v2.7.0"</a>. <i>TensorFlow</i>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20230120082630/https://www.tensorflow.org/api_docs/cc">Archived</a> from the original on January 20, 2023<span class="reference-accessdate">. Retrieved <span class="nowrap">November 6,</span> 2021</span>.</cite></span>

</li>

<li id="cite_note-49"><span class="mw-cite-backlink"><b><a href="#cite_ref-49">^</a></b></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://www.tensorflow.org/api_docs/java/org/tensorflow/package-summary">"org.tensorflow | Java"</a>. <i>TensorFlow</i>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20211106054023/https://www.tensorflow.org/api_docs/java/org/tensorflow/package-summary">Archived</a> from the original on November 6, 2021<span class="reference-accessdate">. Retrieved <span class="nowrap">November 6,</span> 2021</span>.</cite></span>

</li>

<li id="cite_note-50"><span class="mw-cite-backlink"><b><a href="#cite_ref-50">^</a></b></span> <span class="reference-text"><cite id="CITEREFIcaza2018" class="citation web cs1">Icaza, Miguel de (February 17, 2018). <a rel="nofollow" class="external text" href="https://github.com/migueldeicaza/TensorFlowSharp">"TensorFlowSharp: TensorFlow API for .NET languages"</a>. <i><a href="GitHub" title="GitHub">GitHub</a></i>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20170724080201/https://github.com/migueldeicaza/TensorFlowSharp">Archived</a> from the original on July 24, 2017<span class="reference-accessdate">. Retrieved <span class="nowrap">February 18,</span> 2018</span>.</cite></span>

</li>

<li id="cite_note-51"><span class="mw-cite-backlink"><b><a href="#cite_ref-51">^</a></b></span> <span class="reference-text"><cite id="CITEREFChen2018" class="citation web cs1">Chen, Haiping (December 11, 2018). <a rel="nofollow" class="external text" href="https://github.com/SciSharp/TensorFlow.NET">"TensorFlow.NET: .NET Standard bindings for TensorFlow"</a>. <i><a href="GitHub" title="GitHub">GitHub</a></i>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20190712123610/https://github.com/SciSharp/TensorFlow.NET">Archived</a> from the original on July 12, 2019<span class="reference-accessdate">. Retrieved <span class="nowrap">December 11,</span> 2018</span>.</cite></span>

</li>

<li id="cite_note-52"><span class="mw-cite-backlink"><b><a href="#cite_ref-52">^</a></b></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://github.com/tensorflow/haskell">"haskell: Haskell bindings for TensorFlow"</a>. tensorflow. February 17, 2018. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20170724080229/https://github.com/tensorflow/haskell">Archived</a> from the original on July 24, 2017<span class="reference-accessdate">. Retrieved <span class="nowrap">February 18,</span> 2018</span>.</cite></span>

</li>

<li id="cite_note-53"><span class="mw-cite-backlink"><b><a href="#cite_ref-53">^</a></b></span> <span class="reference-text"><cite id="CITEREFMalmaud2019" class="citation web cs1">Malmaud, Jon (August 12, 2019). <a rel="nofollow" class="external text" href="https://github.com/malmaud/TensorFlow.jl">"A Julia wrapper for TensorFlow"</a>. <i><a href="GitHub" title="GitHub">GitHub</a></i>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20170724080234/https://github.com/malmaud/TensorFlow.jl">Archived</a> from the original on July 24, 2017<span class="reference-accessdate">. Retrieved <span class="nowrap">August 14,</span> 2019</span>. <q>operations like sin, * (matrix multiplication), .* (element-wise multiplication), etc [..]. Compare to Python, which requires learning specialized namespaced functions like tf.matmul.</q></cite></span>

</li>

<li id="cite_note-54"><span class="mw-cite-backlink"><b><a href="#cite_ref-54">^</a></b></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://github.com/asteinh/tensorflow.m">"A MATLAB wrapper for TensorFlow Core"</a>. <i><a href="GitHub" title="GitHub">GitHub</a></i>. November 3, 2019. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20200914161638/https://github.com/asteinh/tensorflow.m">Archived</a> from the original on September 14, 2020<span class="reference-accessdate">. Retrieved <span class="nowrap">February 13,</span> 2020</span>.</cite></span>

</li>

<li id="cite_note-55"><span class="mw-cite-backlink"><b><a href="#cite_ref-55">^</a></b></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://github.com/zsoltszakaly/tensorflowforpascal">"Use TensorFlow from Pascal (FreePascal, Lazarus, etc.)"</a>. <i><a href="GitHub" title="GitHub">GitHub</a></i>. January 19, 2023. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20230120083754/https://github.com/zsoltszakaly/tensorflowforpascal">Archived</a> from the original on January 20, 2023<span class="reference-accessdate">. Retrieved <span class="nowrap">January 20,</span> 2023</span>.</cite></span>

</li>

<li id="cite_note-56"><span class="mw-cite-backlink"><b><a href="#cite_ref-56">^</a></b></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://github.com/rstudio/tensorflow">"tensorflow: TensorFlow for R"</a>. RStudio. February 17, 2018. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20170104081359/https://github.com/rstudio/tensorflow">Archived</a> from the original on January 4, 2017<span class="reference-accessdate">. Retrieved <span class="nowrap">February 18,</span> 2018</span>.</cite></span>

</li>

<li id="cite_note-57"><span class="mw-cite-backlink"><b><a href="#cite_ref-57">^</a></b></span> <span class="reference-text"><cite id="CITEREFPlatanios2018" class="citation web cs1">Platanios, Anthony (February 17, 2018). <a rel="nofollow" class="external text" href="https://github.com/eaplatanios/tensorflow_scala">"tensorflow_scala: TensorFlow API for the Scala Programming Language"</a>. <i><a href="GitHub" title="GitHub">GitHub</a></i>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20190218035307/https://github.com/eaplatanios/tensorflow_scala">Archived</a> from the original on February 18, 2019<span class="reference-accessdate">. Retrieved <span class="nowrap">February 18,</span> 2018</span>.</cite></span>

</li>

<li id="cite_note-58"><span class="mw-cite-backlink"><b><a href="#cite_ref-58">^</a></b></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://github.com/tensorflow/rust">"rust: Rust language bindings for TensorFlow"</a>. tensorflow. February 17, 2018. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20170724080245/https://github.com/tensorflow/rust">Archived</a> from the original on July 24, 2017<span class="reference-accessdate">. Retrieved <span class="nowrap">February 18,</span> 2018</span>.</cite></span>

</li>

<li id="cite_note-59"><span class="mw-cite-backlink"><b><a href="#cite_ref-59">^</a></b></span> <span class="reference-text"><cite id="CITEREFMazare2018" class="citation web cs1">Mazare, Laurent (February 16, 2018). <a rel="nofollow" class="external text" href="https://github.com/LaurentMazare/tensorflow-ocaml">"tensorflow-ocaml: OCaml bindings for TensorFlow"</a>. <i><a href="GitHub" title="GitHub">GitHub</a></i>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20180611155059/https://github.com/LaurentMazare/tensorflow-ocaml">Archived</a> from the original on June 11, 2018<span class="reference-accessdate">. Retrieved <span class="nowrap">February 18,</span> 2018</span>.</cite></span>

</li>

<li id="cite_note-60"><span class="mw-cite-backlink"><b><a href="#cite_ref-60">^</a></b></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://github.com/fazibear/tensorflow.cr">"fazibear/tensorflow.cr"</a>. <i>GitHub</i>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20180627120743/https://github.com/fazibear/tensorflow.cr">Archived</a> from the original on June 27, 2018<span class="reference-accessdate">. Retrieved <span class="nowrap">October 10,</span> 2018</span>.</cite></span>

</li>

<li id="cite_note-61"><span class="mw-cite-backlink"><b><a href="#cite_ref-61">^</a></b></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://pkg.go.dev/github.com/tensorflow/tensorflow/tensorflow/go">"tensorflow package - github.com/tensorflow/tensorflow/tensorflow/go - pkg.go.dev"</a>. <i>pkg.go.dev</i>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20211106054028/https://pkg.go.dev/github.com/tensorflow/tensorflow/tensorflow/go">Archived</a> from the original on November 6, 2021<span class="reference-accessdate">. Retrieved <span class="nowrap">November 6,</span> 2021</span>.</cite></span>

</li>

<li id="cite_note-62"><span class="mw-cite-backlink"><b><a href="#cite_ref-62">^</a></b></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://www.tensorflow.org/swift/guide/overview">"Swift for TensorFlow (In Archive Mode)"</a>. <i>TensorFlow</i>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20211106054024/https://www.tensorflow.org/swift/guide/overview">Archived</a> from the original on November 6, 2021<span class="reference-accessdate">. Retrieved <span class="nowrap">November 6,</span> 2021</span>.</cite></span>

</li>

<li id="cite_note-63"><span class="mw-cite-backlink"><b><a href="#cite_ref-63">^</a></b></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://www.tensorflow.org/js">"TensorFlow.js | Machine Learning for JavaScript Developers"</a>. <i>TensorFlow</i>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20211104081918/https://www.tensorflow.org/js/">Archived</a> from the original on November 4, 2021<span class="reference-accessdate">. Retrieved <span class="nowrap">October 28,</span> 2021</span>.</cite></span>

</li>

<li id="cite_note-64"><span class="mw-cite-backlink"><b><a href="#cite_ref-64">^</a></b></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://ai.google.dev/edge/litert">"LiteRT Overview | Google AI Edge"</a>. <i>Google AI for Developers</i><span class="reference-accessdate">. Retrieved <span class="nowrap">May 7,</span> 2025</span>.</cite></span>

</li>

<li id="cite_note-65"><span class="mw-cite-backlink"><b><a href="#cite_ref-65">^</a></b></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://www.tensorflow.org/lite">"TensorFlow Lite | ML for Mobile and Edge Devices"</a>. <i>TensorFlow</i>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20211104011324/https://www.tensorflow.org/lite">Archived</a> from the original on November 4, 2021<span class="reference-accessdate">. Retrieved <span class="nowrap">November 1,</span> 2021</span>.</cite></span>

</li>

<li id="cite_note-:14-66"><span class="mw-cite-backlink">^ <a href="#cite_ref-:14_66-0"><sup><i><b>a</b></i></sup></a> <a href="#cite_ref-:14_66-1"><sup><i><b>b</b></i></sup></a></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://www.tensorflow.org/lite/guide">"TensorFlow Lite"</a>. <i>TensorFlow</i>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20211102150551/https://www.tensorflow.org/lite/guide">Archived</a> from the original on November 2, 2021<span class="reference-accessdate">. Retrieved <span class="nowrap">November 1,</span> 2021</span>.</cite></span>

</li>

<li id="cite_note-:2-67"><span class="mw-cite-backlink">^ <a href="#cite_ref-:2_67-0"><sup><i><b>a</b></i></sup></a> <a href="#cite_ref-:2_67-1"><sup><i><b>b</b></i></sup></a></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://www.tensorflow.org/tfx">"TensorFlow Extended (TFX) | ML Production Pipelines"</a>. <i>TensorFlow</i>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20211104005652/https://www.tensorflow.org/tfx">Archived</a> from the original on November 4, 2021<span class="reference-accessdate">. Retrieved <span class="nowrap">November 2,</span> 2021</span>.</cite></span>

</li>

<li id="cite_note-:15-68"><span class="mw-cite-backlink">^ <a href="#cite_ref-:15_68-0"><sup><i><b>a</b></i></sup></a> <a href="#cite_ref-:15_68-1"><sup><i><b>b</b></i></sup></a> <a href="#cite_ref-:15_68-2"><sup><i><b>c</b></i></sup></a></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://www.tensorflow.org/tutorials/customization/basics">"Customization basics: tensors and operations | TensorFlow Core"</a>. <i>TensorFlow</i>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20211106055823/https://www.tensorflow.org/tutorials/customization/basics">Archived</a> from the original on November 6, 2021<span class="reference-accessdate">. Retrieved <span class="nowrap">November 6,</span> 2021</span>.</cite></span>

</li>

<li id="cite_note-:33-69"><span class="mw-cite-backlink">^ <a href="#cite_ref-:33_69-0"><sup><i><b>a</b></i></sup></a> <a href="#cite_ref-:33_69-1"><sup><i><b>b</b></i></sup></a></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://www.tensorflow.org/guide">"Guide | TensorFlow Core"</a>. <i>TensorFlow</i>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20190717021617/https://www.tensorflow.org/guide">Archived</a> from the original on July 17, 2019<span class="reference-accessdate">. Retrieved <span class="nowrap">November 4,</span> 2021</span>.</cite></span>

</li>

<li id="cite_note-:43-70"><span class="mw-cite-backlink">^ <a href="#cite_ref-:43_70-0"><sup><i><b>a</b></i></sup></a> <a href="#cite_ref-:43_70-1"><sup><i><b>b</b></i></sup></a></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://www.tensorflow.org/resources/libraries-extensions">"Libraries & extensions"</a>. <i>TensorFlow</i>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20211104012048/https://www.tensorflow.org/resources/libraries-extensions">Archived</a> from the original on November 4, 2021<span class="reference-accessdate">. Retrieved <span class="nowrap">November 4,</span> 2021</span>.</cite></span>

</li>

<li id="cite_note-71"><span class="mw-cite-backlink"><b><a href="#cite_ref-71">^</a></b></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://research.google.com/colaboratory/faq.html">"Colaboratory – Google"</a>. <i>research.google.com</i>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20171024191457/https://research.google.com/colaboratory/faq.html">Archived</a> from the original on October 24, 2017<span class="reference-accessdate">. Retrieved <span class="nowrap">November 10,</span> 2018</span>.</cite></span>

</li>

<li id="cite_note-72"><span class="mw-cite-backlink"><b><a href="#cite_ref-72">^</a></b></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://colab.research.google.com/">"Google Colaboratory"</a>. <i>colab.research.google.com</i>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20210203141626/https://colab.research.google.com/">Archived</a> from the original on February 3, 2021<span class="reference-accessdate">. Retrieved <span class="nowrap">November 6,</span> 2021</span>.</cite></span>

</li>

<li id="cite_note-:jax-73"><span class="mw-cite-backlink">^ <a href="#cite_ref-:jax_73-0"><sup><i><b>a</b></i></sup></a> <a href="#cite_ref-:jax_73-1"><sup><i><b>b</b></i></sup></a></span> <span class="reference-text"><cite id="CITEREFBradburyFrostigHawkinsJohnson2022" class="citation cs2">Bradbury, James; Frostig, Roy; Hawkins, Peter; Johnson, Matthew James; Leary, Chris; MacLaurin, Dougal; Necula, George; Paszke, Adam; Vanderplas, Jake; Wanderman-Milne, Skye; Zhang, Qiao (June 18, 2022), <a rel="nofollow" class="external text" href="https://web.archive.org/web/20220618205214/https://github.com/google/jax">"JAX: Autograd and XLA"</a>, <i>Astrophysics Source Code Library</i>, Google, <a href="Bibcode_(identifier)" class="mw-redirect" title="Bibcode (identifier)">Bibcode</a>:<a rel="nofollow" class="external text" href="https://ui.adsabs.harvard.edu/abs/2021ascl.soft11002B">2021ascl.soft11002B</a>, archived from <a rel="nofollow" class="external text" href="https://github.com/google/jax">the original</a> on June 18, 2022<span class="reference-accessdate">, retrieved <span class="nowrap">June 18,</span> 2022</span></cite></span>

</li>

<li id="cite_note-74"><span class="mw-cite-backlink"><b><a href="#cite_ref-74">^</a></b></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://www.deepmind.com/blog/using-jax-to-accelerate-our-research">"Using JAX to accelerate our research"</a>. <i>www.deepmind.com</i>. December 4, 2020. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20220618205746/https://www.deepmind.com/blog/using-jax-to-accelerate-our-research">Archived</a> from the original on June 18, 2022<span class="reference-accessdate">. Retrieved <span class="nowrap">June 18,</span> 2022</span>.</cite></span>

</li>

<li id="cite_note-75"><span class="mw-cite-backlink"><b><a href="#cite_ref-75">^</a></b></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://analyticsindiamag.com/why-is-googles-jax-so-popular/">"Why is Google's JAX so popular?"</a>. <i>Analytics India Magazine</i>. April 25, 2022. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20220618210503/https://analyticsindiamag.com/why-is-googles-jax-so-popular/">Archived</a> from the original on June 18, 2022<span class="reference-accessdate">. Retrieved <span class="nowrap">June 18,</span> 2022</span>.</cite></span>

</li>

<li id="cite_note-76"><span class="mw-cite-backlink"><b><a href="#cite_ref-76">^</a></b></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://blog.tensorflow.org/2019/03/intelligent-scanning-using-deep-learning.html">"Intelligent Scanning Using Deep Learning for MRI"</a>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20211104183851/https://blog.tensorflow.org/2019/03/intelligent-scanning-using-deep-learning.html">Archived</a> from the original on November 4, 2021<span class="reference-accessdate">. Retrieved <span class="nowrap">November 4,</span> 2021</span>.</cite></span>

</li>

<li id="cite_note-:6-77"><span class="mw-cite-backlink">^ <a href="#cite_ref-:6_77-0"><sup><i><b>a</b></i></sup></a> <a href="#cite_ref-:6_77-1"><sup><i><b>b</b></i></sup></a> <a href="#cite_ref-:6_77-2"><sup><i><b>c</b></i></sup></a> <a href="#cite_ref-:6_77-3"><sup><i><b>d</b></i></sup></a></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://www.tensorflow.org/about/case-studies">"Case Studies and Mentions"</a>. <i>TensorFlow</i>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20211026011835/https://www.tensorflow.org/about/case-studies">Archived</a> from the original on October 26, 2021<span class="reference-accessdate">. Retrieved <span class="nowrap">November 4,</span> 2021</span>.</cite></span>

</li>

<li id="cite_note-:7-78"><span class="mw-cite-backlink">^ <a href="#cite_ref-:7_78-0"><sup><i><b>a</b></i></sup></a> <a href="#cite_ref-:7_78-1"><sup><i><b>b</b></i></sup></a></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://blog.tensorflow.org/2019/03/ranking-tweets-with-tensorflow.html">"Ranking Tweets with TensorFlow"</a>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20211104005536/https://blog.tensorflow.org/2019/03/ranking-tweets-with-tensorflow.html">Archived</a> from the original on November 4, 2021<span class="reference-accessdate">. Retrieved <span class="nowrap">November 4,</span> 2021</span>.</cite></span>

</li>

<li id="cite_note-79"><span class="mw-cite-backlink"><b><a href="#cite_ref-79">^</a></b></span> <span class="reference-text"><cite id="CITEREFDavies2020" class="citation web cs1">Davies, Dave (September 2, 2020). <a rel="nofollow" class="external text" href="https://www.searchenginejournal.com/google-algorithm-history/rankbrain/">"A Complete Guide to the Google RankBrain Algorithm"</a>. <i>Search Engine Journal</i>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20211106062307/https://www.searchenginejournal.com/google-algorithm-history/rankbrain/">Archived</a> from the original on November 6, 2021<span class="reference-accessdate">. Retrieved <span class="nowrap">October 15,</span> 2024</span>.</cite></span>

</li>

<li id="cite_note-80"><span class="mw-cite-backlink"><b><a href="#cite_ref-80">^</a></b></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://blog.tensorflow.org/2020/12/inspace-new-video-conferencing-platform-uses-tensorflowjs-for-toxicity-filters-in-chat.html">"InSpace: A new video conferencing platform that uses TensorFlow.js for toxicity filters in chat"</a>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20211104005535/https://blog.tensorflow.org/2020/12/inspace-new-video-conferencing-platform-uses-tensorflowjs-for-toxicity-filters-in-chat.html">Archived</a> from the original on November 4, 2021<span class="reference-accessdate">. Retrieved <span class="nowrap">November 4,</span> 2021</span>.</cite></span>

</li>

<li id="cite_note-:8-81"><span class="mw-cite-backlink">^ <a href="#cite_ref-:8_81-0"><sup><i><b>a</b></i></sup></a> <a href="#cite_ref-:8_81-1"><sup><i><b>b</b></i></sup></a></span> <span class="reference-text"><cite id="CITEREFXulin" class="citation web cs1">Xulin. <a rel="nofollow" class="external text" href="http://mp.weixin.qq.com/s?__biz=MzI0NjIzNDkwOA==&mid=2247484035&idx=1&sn=85fa0decac95e359435f68c50865ac0b&chksm=e94328f0de34a1e665e0d809b938efb34f0aa6034391891246fc223b7782ac3bfd6ddd588aa2#rd">"流利说基于 TensorFlow 的自适应系统实践"</a>. <i>Weixin Official Accounts Platform</i>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20211106224313/https://mp.weixin.qq.com/s?__biz=MzI0NjIzNDkwOA==&mid=2247484035&idx=1&sn=85fa0decac95e359435f68c50865ac0b&chksm=e94328f0de34a1e665e0d809b938efb34f0aa6034391891246fc223b7782ac3bfd6ddd588aa2#rd">Archived</a> from the original on November 6, 2021<span class="reference-accessdate">. Retrieved <span class="nowrap">November 4,</span> 2021</span>.</cite></span>

</li>

<li id="cite_note-82"><span class="mw-cite-backlink"><b><a href="#cite_ref-82">^</a></b></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://blog.tensorflow.org/2020/02/how-modiface-utilized-tensorflowjs-in-ar-makeup-in-browser.html">"How Modiface utilized TensorFlow.js in production for AR makeup try on in the browser"</a>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20211104005535/https://blog.tensorflow.org/2020/02/how-modiface-utilized-tensorflowjs-in-ar-makeup-in-browser.html">Archived</a> from the original on November 4, 2021<span class="reference-accessdate">. Retrieved <span class="nowrap">November 4,</span> 2021</span>.</cite></span>

</li>

<li id="cite_note-Byrne-83"><span class="mw-cite-backlink"><b><a href="#cite_ref-Byrne_83-0">^</a></b></span> <span class="reference-text"><cite id="CITEREFByrne2015" class="citation web cs1">Byrne, Michael (November 11, 2015). <a rel="nofollow" class="external text" href="https://www.vice.com/en/article/google-offers-up-its-entire-machine-learning-library-as-open-source/">"Google Offers Up Its Entire Machine Learning Library as Open-Source Software"</a>. <i>Vice</i>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20210125121138/https://www.vice.com/en/article/8q8avx/google-offers-up-its-entire-machine-learning-library-as-open-source">Archived</a> from the original on January 25, 2021<span class="reference-accessdate">. Retrieved <span class="nowrap">November 11,</span> 2015</span>.</cite></span>

</li>

</ol></div></div>

<div class="mw-heading mw-heading2"><h2 id="Further_reading">Further reading</h2></div>

/* start https://en.wikipedia.org/ */

.mw-parser-output .refbegin{margin-bottom:0.5em}.mw-parser-output .refbegin-hanging-indents>ul{margin-left:0}.mw-parser-output .refbegin-hanging-indents>ul>li{margin-left:0;padding-left:3.2em;text-indent:-3.2em}.mw-parser-output .refbegin-hanging-indents ul,.mw-parser-output .refbegin-hanging-indents ul li{list-style:none}@media(max-width:720px){.mw-parser-output .refbegin-hanging-indents>ul>li{padding-left:1.6em;text-indent:-1.6em}}.mw-parser-output .refbegin-columns{margin-top:0.3em}.mw-parser-output .refbegin-columns ul{margin-top:0}.mw-parser-output .refbegin-columns li{page-break-inside:avoid;break-inside:avoid-column}@media screen{.mw-parser-output .refbegin{font-size:90%}}

/* end https://en.wikipedia.org/ */

</style><div class="refbegin" style="">

<ul><li><cite id="CITEREFMoroney2020" class="citation book cs1">Moroney, Laurence (October 1, 2020). <a rel="nofollow" class="external text" href="https://www.oreilly.com/library/view/ai-and-machine/9781492078180/"><i>AI and Machine Learning for Coders</i></a> (1st ed.). <a href="O'Reilly_Media" title="O'Reilly Media">O'Reilly Media</a>. p. 365. <a href="ISBN_(identifier)" class="mw-redirect" title="ISBN (identifier)">ISBN</a> <bdi>9781492078197</bdi>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20210607074743/https://www.oreilly.com/library/view/ai-and-machine/9781492078180/">Archived</a> from the original on June 7, 2021<span class="reference-accessdate">. Retrieved <span class="nowrap">December 21,</span> 2020</span>.</cite></li>

<li><cite id="CITEREFGéron2019" class="citation book cs1">Géron, Aurélien (October 15, 2019). <a rel="nofollow" class="external text" href="https://www.oreilly.com/library/view/hands-on-machine-learning/9781492032632/"><i>Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow</i></a> (2nd ed.). <a href="O'Reilly_Media" title="O'Reilly Media">O'Reilly Media</a>. p. 856. <a href="ISBN_(identifier)" class="mw-redirect" title="ISBN (identifier)">ISBN</a> <bdi>9781492032632</bdi>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20210501010926/https://www.oreilly.com/library/view/hands-on-machine-learning/9781492032632/">Archived</a> from the original on May 1, 2021<span class="reference-accessdate">. Retrieved <span class="nowrap">November 25,</span> 2019</span>.</cite></li>

<li><cite id="CITEREFRamsundarZadeh2018" class="citation book cs1">Ramsundar, Bharath; Zadeh, Reza Bosagh (March 23, 2018). <a rel="nofollow" class="external text" href="https://www.oreilly.com/library/view/tensorflow-for-deep/9781491980446/"><i>TensorFlow for Deep Learning</i></a> (1st ed.). <a href="O'Reilly_Media" title="O'Reilly Media">O'Reilly Media</a>. p. 256. <a href="ISBN_(identifier)" class="mw-redirect" title="ISBN (identifier)">ISBN</a> <bdi>9781491980446</bdi>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20210607150529/https://www.oreilly.com/library/view/tensorflow-for-deep/9781491980446/">Archived</a> from the original on June 7, 2021<span class="reference-accessdate">. Retrieved <span class="nowrap">November 25,</span> 2019</span>.</cite></li>

<li><cite id="CITEREFHopeResheffLieder2017" class="citation book cs1">Hope, Tom; Resheff, Yehezkel S.; Lieder, Itay (August 27, 2017). <a rel="nofollow" class="external text" href="https://www.oreilly.com/library/view/learning-tensorflow/9781491978504/"><i>Learning TensorFlow: A Guide to Building Deep Learning Systems</i></a> (1st ed.). <a href="O'Reilly_Media" title="O'Reilly Media">O'Reilly Media</a>. p. 242. <a href="ISBN_(identifier)" class="mw-redirect" title="ISBN (identifier)">ISBN</a> <bdi>9781491978504</bdi>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20210308153359/https://www.oreilly.com/library/view/learning-tensorflow/9781491978504/">Archived</a> from the original on March 8, 2021<span class="reference-accessdate">. Retrieved <span class="nowrap">November 25,</span> 2019</span>.</cite></li>

<li><cite id="CITEREFShukla2018" class="citation book cs1">Shukla, Nishant (February 12, 2018). <i>Machine Learning with TensorFlow</i> (1st ed.). <a href="Manning_Publications" title="Manning Publications">Manning Publications</a>. p. 272. <a href="ISBN_(identifier)" class="mw-redirect" title="ISBN (identifier)">ISBN</a> <bdi>9781617293870</bdi>.</cite></li></ul>

</div>

<div class="mw-heading mw-heading2"><h2 id="External_links">External links</h2></div>

<ul><li><span class="official-website"><span class="url"><a rel="nofollow" class="external text" href="http://www.tensorflow.org">Official website</a></span></span></li>

<li><a rel="nofollow" class="external text" href="https://www.oreilly.com/library/view/learning-tensorflowjs/9781492090786/">Learning TensorFlow.js Book (ENG)</a></li></ul>

/* start https://en.wikipedia.org/ */

.mw-parser-output .navbox{box-sizing:border-box;border:1px solid #a2a9b1;width:100%;clear:both;font-size:88%;text-align:center;padding:1px;margin:1em auto 0}.mw-parser-output .navbox .navbox{margin-top:0}.mw-parser-output .navbox+.navbox,.mw-parser-output .navbox+.navbox-styles+.navbox{margin-top:-1px}.mw-parser-output .navbox-inner,.mw-parser-output .navbox-subgroup{width:100%}.mw-parser-output .navbox-group,.mw-parser-output .navbox-title,.mw-parser-output .navbox-abovebelow{padding:0.25em 1em;line-height:1.5em;text-align:center}.mw-parser-output .navbox-group{white-space:nowrap;text-align:right}.mw-parser-output .navbox,.mw-parser-output .navbox-subgroup{background-color:#fdfdfd}.mw-parser-output .navbox-list{line-height:1.5em;border-color:#fdfdfd}.mw-parser-output .navbox-list-with-group{text-align:left;border-left-width:2px;border-left-style:solid}.mw-parser-output tr+tr>.navbox-abovebelow,.mw-parser-output tr+tr>.navbox-group,.mw-parser-output tr+tr>.navbox-image,.mw-parser-output tr+tr>.navbox-list{border-top:2px solid #fdfdfd}.mw-parser-output .navbox-title{background-color:#ccf}.mw-parser-output .navbox-abovebelow,.mw-parser-output .navbox-group,.mw-parser-output .navbox-subgroup .navbox-title{background-color:#ddf}.mw-parser-output .navbox-subgroup .navbox-group,.mw-parser-output .navbox-subgroup .navbox-abovebelow{background-color:#e6e6ff}.mw-parser-output .navbox-even{background-color:#f7f7f7}.mw-parser-output .navbox-odd{background-color:transparent}.mw-parser-output .navbox .hlist td dl,.mw-parser-output .navbox .hlist td ol,.mw-parser-output .navbox .hlist td ul,.mw-parser-output .navbox td.hlist dl,.mw-parser-output .navbox td.hlist ol,.mw-parser-output .navbox td.hlist ul{padding:0.125em 0}.mw-parser-output .navbox .navbar{display:block;font-size:100%}.mw-parser-output .navbox-title .navbar{float:left;text-align:left;margin-right:0.5em}body.skin--responsive .mw-parser-output .navbox-image img{max-width:none!important}@media print{body.ns-0 .mw-parser-output .navbox{display:none!important}}

/* end https://en.wikipedia.org/ */

</style></div><div role="navigation" class="navbox" aria-labelledby="Google_AI352" style="padding:3px"><table class="nowraplinks hlist mw-collapsible autocollapse navbox-inner" style="border-spacing:0;background:transparent;color:inherit"><tbody><tr><th scope="col" class="navbox-title" colspan="2"><div id="Google_AI352" style="font-size:114%;margin:0 4em"><a href="Google_AI" title="Google AI">Google AI</a></div></th></tr><tr><td class="navbox-abovebelow" colspan="2"><div>

<ul><li><a href="Google" title="Google">Google</a></li>

<li><a href="Google_Brain" title="Google Brain">Google Brain</a></li>

<li><a href="Google_DeepMind" title="Google DeepMind">Google DeepMind</a></li></ul>

</div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%">Computer programs</th><td class="navbox-list-with-group navbox-list navbox-odd" style="width:100%;padding:0"><div style="padding:0 0.25em"></div><table class="nowraplinks navbox-subgroup" style="border-spacing:0"><tbody><tr><th scope="row" class="navbox-group" style="width:1%">AlphaGo</th><td class="navbox-list-with-group navbox-list navbox-odd" style="width:100%;padding:0"><div style="padding:0 0.25em"></div><table class="nowraplinks navbox-subgroup" style="border-spacing:0"><tbody><tr><th scope="row" class="navbox-group" style="width:1%">Versions</th><td class="navbox-list-with-group navbox-list navbox-odd" style="width:100%;padding:0"><div style="padding:0 0.25em">

<ul><li><a href="AlphaGo" title="AlphaGo">AlphaGo</a> (2015)</li>

<li><a href="Master_(software)" title="Master (software)">Master</a> (2016)</li>

<li><a href="AlphaGo_Zero" title="AlphaGo Zero">AlphaGo Zero</a> (2017)</li>

<li><a href="AlphaZero" title="AlphaZero">AlphaZero</a> (2017)</li>

<li><a href="MuZero" title="MuZero">MuZero</a> (2019)</li></ul>

</div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%">Competitions</th><td class="navbox-list-with-group navbox-list navbox-even" style="width:100%;padding:0"><div style="padding:0 0.25em">

<li><a href="AlphaGo_versus_Lee_Sedol" title="AlphaGo versus Lee Sedol">Lee Sedol</a> (2016)</li>

</div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%">In popular culture</th><td class="navbox-list-with-group navbox-list navbox-odd" style="width:100%;padding:0"><div style="padding:0 0.25em">

<ul><li><i><a href="AlphaGo_(film)" title="AlphaGo (film)">AlphaGo</a></i> (2017)</li>

<li><i><a href="The_MANIAC" title="The MANIAC">The MANIAC</a></i> (2023)</li></ul>

</div></td></tr></tbody></table><div></div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%">Other</th><td class="navbox-list-with-group navbox-list navbox-even" style="width:100%;padding:0"><div style="padding:0 0.25em">

<ul><li><a href="AlphaFold" title="AlphaFold">AlphaFold</a> (2018)</li>

<li><a href="AlphaStar_(software)" title="AlphaStar (software)">AlphaStar</a> (2019)</li>

<li><a href="AlphaDev" title="AlphaDev">AlphaDev</a> (2023)</li>

<li><a href="AlphaGeometry" title="AlphaGeometry">AlphaGeometry</a> (2024)</li>

<li><a href="AlphaGenome" title="AlphaGenome">AlphaGenome</a> (2025)</li></ul>

</div></td></tr></tbody></table><div></div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%">Machine learning</th><td class="navbox-list-with-group navbox-list navbox-odd" style="width:100%;padding:0"><div style="padding:0 0.25em"></div><table class="nowraplinks navbox-subgroup" style="border-spacing:0"><tbody><tr><th scope="row" class="navbox-group" style="width:1%">Neural networks</th><td class="navbox-list-with-group navbox-list navbox-odd" style="width:100%;padding:0"><div style="padding:0 0.25em">

<ul><li><a href="Inception_(deep_learning_architecture)" title="Inception (deep learning architecture)">Inception</a> (2014)</li>

<li><a href="WaveNet" title="WaveNet">WaveNet</a> (2016)</li>

<li><a href="MobileNet" title="MobileNet">MobileNet</a> (2017)</li>

<li><a href="Transformer_(deep_learning_architecture)" title="Transformer (deep learning architecture)">Transformer</a> (2017)</li>

<li><a href="EfficientNet" title="EfficientNet">EfficientNet</a> (2019)</li>

</div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%">Other</th><td class="navbox-list-with-group navbox-list navbox-even" style="width:100%;padding:0"><div style="padding:0 0.25em">

<ul><li><a href="Quantum_Artificial_Intelligence_Lab" title="Quantum Artificial Intelligence Lab">Quantum Artificial Intelligence Lab</a></li>

<li><a href="Tensor_Processing_Unit" title="Tensor Processing Unit">Tensor Processing Unit</a></li></ul>

</div></td></tr></tbody></table><div></div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%">Generative AI</th><td class="navbox-list-with-group navbox-list navbox-odd" style="width:100%;padding:0"><div style="padding:0 0.25em"></div><table class="nowraplinks navbox-subgroup" style="border-spacing:0"><tbody><tr><th scope="row" class="navbox-group" style="width:1%">Chatbots</th><td class="navbox-list-with-group navbox-list navbox-odd" style="width:100%;padding:0"><div style="padding:0 0.25em">

<ul><li><a href="Google_Assistant" title="Google Assistant">Assistant</a> (2016)</li>

<li><a href="Sparrow_(chatbot)" title="Sparrow (chatbot)">Sparrow</a> (2022)</li>

<li><a href="Gemini_(chatbot)" title="Gemini (chatbot)">Gemini</a> (2023)</li></ul>

</div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%">Models</th><td class="navbox-list-with-group navbox-list navbox-even" style="width:100%;padding:0"><div style="padding:0 0.25em">

<li><a href="XLNet" title="XLNet">XLNet</a> (2019)</li>

<li><a href="LaMDA" title="LaMDA">LaMDA</a> (2021)</li>

<li><a href="Chinchilla_(language_model)" title="Chinchilla (language model)">Chinchilla</a> (2022)</li>

<li><a href="Imagen_(text-to-image_model)" title="Imagen (text-to-image model)">Imagen</a> (2023)</li>

<li><a href="Gemini_(language_model)" title="Gemini (language model)">Gemini</a> (2023)</li>

<li><a href="VideoPoet" title="VideoPoet">VideoPoet</a> (2024)</li>

</div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%">Other</th><td class="navbox-list-with-group navbox-list navbox-odd" style="width:100%;padding:0"><div style="padding:0 0.25em">

<ul><li><a href="DreamBooth" title="DreamBooth">DreamBooth</a> (2022)</li>

<li><a href="NotebookLM" title="NotebookLM">NotebookLM</a> (2023)</li>

<li><a href="Gemini_Robotics" title="Gemini Robotics">Gemini Robotics</a> (2025)</li></ul>

</div></td></tr></tbody></table><div></div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%">See also</th><td class="navbox-list-with-group navbox-list navbox-even" style="width:100%;padding:0"><div style="padding:0 0.25em">

<ul><li>"<a href="Attention_Is_All_You_Need" title="Attention Is All You Need">Attention Is All You Need</a>"</li>

<li><a href="Future_of_Go_Summit" title="Future of Go Summit">Future of Go Summit</a></li>

<li><a href="Generative_pre-trained_transformer" title="Generative pre-trained transformer">Generative pre-trained transformer</a></li>

<li><a href="Google_Labs" title="Google Labs">Google Labs</a></li>

<li><a href="Google_Pixel" title="Google Pixel">Google Pixel</a></li>

<li><a href="Google_Workspace" title="Google Workspace">Google Workspace</a></li>

<li><a href="Robot_Constitution" title="Robot Constitution">Robot Constitution</a></li></ul>

</div></td></tr><tr><td class="navbox-abovebelow" colspan="2"><div>

<ul><li><span class="noviewer" typeof="mw:File"><span title="Category"></span></span> Category</li>

<li><span class="noviewer" typeof="mw:File"><span title="Commons page"></span></span> <a href="https://commons.wikimedia.org/wiki/Category:DeepMind" class="extiw external" title="commons:Category:DeepMind">Commons</a></li></ul>

</div></td></tr></tbody></table></div>

<div class="navbox-styles"></div><div role="navigation" class="navbox" aria-labelledby="Deep_learning_software304" style="padding:3px"><table class="nowraplinks hlist mw-collapsible autocollapse navbox-inner" style="border-spacing:0;background:transparent;color:inherit"><tbody><tr><th scope="col" class="navbox-title" colspan="2"><div id="Deep_learning_software304" style="font-size:114%;margin:0 4em"><a href="Comparison_of_deep_learning_software" title="Comparison of deep learning software">Deep learning software</a></div></th></tr><tr><td class="navbox-abovebelow" colspan="2"><div>

<ul><li><a href="Comparison_of_deep_learning_software" title="Comparison of deep learning software">Comparison</a></li></ul>

</div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%"><a href="Open-source_software" title="Open-source software">Open source</a></th><td class="navbox-list-with-group navbox-list navbox-odd" style="width:100%;padding:0"><div style="padding:0 0.25em">

<ul><li><a href="Apache_MXNet" title="Apache MXNet">Apache MXNet</a></li>

<li><a href="Apache_SINGA" title="Apache SINGA">Apache SINGA</a></li>

<li><a href="Caffe_(software)" title="Caffe (software)">Caffe</a></li>

<li><a href="Deeplearning4j" title="Deeplearning4j">Deeplearning4j</a></li>

<li><a href="DeepSpeed" title="DeepSpeed">DeepSpeed</a></li>

<li><a href="Keras" title="Keras">Keras</a></li>

<li><a href="Microsoft_Cognitive_Toolkit" title="Microsoft Cognitive Toolkit">Microsoft Cognitive Toolkit</a></li>

<li><a href="OpenNN" title="OpenNN">OpenNN</a></li>

<li><a href="PyTorch" title="PyTorch">PyTorch</a></li>

<li><a href="Theano_(software)" title="Theano (software)">Theano</a></li>

<li><a href="Torch_(machine_learning)" title="Torch (machine learning)">Torch</a></li>

<li><a href="OpenVINO" title="OpenVINO">OpenVINO</a></li>

<li><a href="MindSpore" title="MindSpore">MindSpore</a></li></ul>

</div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%"><a href="Proprietary_software" title="Proprietary software">Proprietary</a></th><td class="navbox-list-with-group navbox-list navbox-even" style="width:100%;padding:0"><div style="padding:0 0.25em">

<ul><li><a href="Apple_Inc." title="Apple Inc.">Apple</a> <a href="Core_ML" class="mw-redirect" title="Core ML">Core ML</a></li>

<li><a href="Watson_(computer)" class="mw-redirect" title="Watson (computer)">IBM Watson</a></li>

<li><a href="Neural_Designer" title="Neural Designer">Neural Designer</a></li>

<li><a href="Wolfram_Mathematica" class="mw-redirect" title="Wolfram Mathematica">Wolfram Mathematica</a></li>

<li><a href="MATLAB" title="MATLAB">MATLAB</a> Deep Learning Toolbox</li></ul>

</div></td></tr><tr><td class="navbox-abovebelow" colspan="2"><div>

<ul><li><span class="noviewer" typeof="mw:File"><span title="Category"></span></span> Category</li></ul>

</div></td></tr></tbody></table></div>

<div class="navbox-styles"></div><div role="navigation" class="navbox" aria-labelledby="Differentiable_computing254" style="padding:3px"><table class="nowraplinks hlist mw-collapsible autocollapse navbox-inner" style="border-spacing:0;background:transparent;color:inherit"><tbody><tr><th scope="col" class="navbox-title" colspan="2"><div id="Differentiable_computing254" style="font-size:114%;margin:0 4em">Differentiable computing</div></th></tr><tr><th scope="row" class="navbox-group" style="width:1%"><a href="Differentiable_function" title="Differentiable function">General</a></th><td class="navbox-list-with-group navbox-list navbox-odd" style="width:100%;padding:0"><div style="padding:0 0.25em">

<ul><li><b><a href="Differentiable_programming" title="Differentiable programming">Differentiable programming</a></b></li>

<li><a href="Information_geometry" title="Information geometry">Information geometry</a></li>

<li><a href="Statistical_manifold" title="Statistical manifold">Statistical manifold</a></li>

<li><a href="Automatic_differentiation" title="Automatic differentiation">Automatic differentiation</a></li>

<li><a href="Neuromorphic_computing" title="Neuromorphic computing">Neuromorphic computing</a></li>

<li><a href="Pattern_recognition" title="Pattern recognition">Pattern recognition</a></li>

<li><a href="Ricci_calculus" title="Ricci calculus">Ricci calculus</a></li>

<li><a href="Computational_learning_theory" title="Computational learning theory">Computational learning theory</a></li>

<li><a href="Inductive_bias" title="Inductive bias">Inductive bias</a></li></ul>

</div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%">Hardware</th><td class="navbox-list-with-group navbox-list navbox-even" style="width:100%;padding:0"><div style="padding:0 0.25em">

<li><a href="Memristor" title="Memristor">Memristor</a></li>

<li><a href="SpiNNaker" title="SpiNNaker">SpiNNaker</a></li></ul>

</div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%">Software libraries</th><td class="navbox-list-with-group navbox-list navbox-odd" style="width:100%;padding:0"><div style="padding:0 0.25em">

<ul>

<li><a href="PyTorch" title="PyTorch">PyTorch</a></li>

<li><a href="Keras" title="Keras">Keras</a></li>

<li><a href="Scikit-learn" title="Scikit-learn">scikit-learn</a></li>

<li><a href="Theano_(software)" title="Theano (software)">Theano</a></li>

<li><a href="MindSpore" title="MindSpore">MindSpore</a></li></ul>

</div></td></tr><tr><td class="navbox-abovebelow" colspan="2"><div>

<ul><li><span class="noviewer" typeof="mw:File"></span> Portals

<ul><li><a href="Portal%3AComputer_programming" title="Portal:Computer programming">Computer programming</a></li>

<li><a href="Portal%3ATechnology" title="Portal:Technology">Technology</a></li></ul></li></ul>

</div></td></tr></tbody></table></div>

<div class="navbox-styles"></div><div role="navigation" class="navbox" aria-labelledby="Google_free_and_open-source_software55" style="padding:3px"><table class="nowraplinks mw-collapsible autocollapse navbox-inner" style="border-spacing:0;background:transparent;color:inherit"><tbody><tr><th scope="col" class="navbox-title" colspan="2"><div id="Google_free_and_open-source_software55" style="font-size:114%;margin:0 4em"><a href="Google" title="Google">Google</a> free and open-source software</div></th></tr><tr><th scope="row" class="navbox-group" style="width:1%">Software</th><td class="navbox-list-with-group navbox-list navbox-odd hlist" style="width:100%;padding:0"><div style="padding:0 0.25em"></div><table class="nowraplinks navbox-subgroup" style="border-spacing:0"><tbody><tr><th scope="row" class="navbox-group" style="width:1%">Applications</th><td class="navbox-list-with-group navbox-list navbox-odd" style="width:100%;padding:0"><div style="padding:0 0.25em">

<ul><li><a href="Chromium_(web_browser)" title="Chromium (web browser)">Chromium</a></li>

<li><a href="Gemini_(language_model)" title="Gemini (language model)">Gemma</a></li>

<li><a href="OpenRefine" title="OpenRefine">OpenRefine</a></li>

<li><a href="Tesseract_(software)" title="Tesseract (software)">Tesseract</a></li></ul>

</div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%">Programming languages</th><td class="navbox-list-with-group navbox-list navbox-even" style="width:100%;padding:0"><div style="padding:0 0.25em">

<ul><li><a href="Carbon_(programming_language)" title="Carbon (programming language)">Carbon</a></li>

<li><a href="Sawzall_(programming_language)" title="Sawzall (programming language)">Sawzall</a></li></ul>

</div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%">Frameworks and<br>development tools</th><td class="navbox-list-with-group navbox-list navbox-odd" style="width:100%;padding:0"><div style="padding:0 0.25em">

<li><a href="Angular_(web_framework)" title="Angular (web framework)">Angular</a></li>

<li><a href="AngularJS" title="AngularJS">AngularJS</a></li>

<li><a href="Bazel_(software)" title="Bazel (software)">Bazel</a></li>

<li><a href="Blockly" title="Blockly">Blockly</a></li>

<li><a href="Brotli" title="Brotli">Brotli</a></li>

<li><a href="Google_Closure_Tools" title="Google Closure Tools">Closure Tools</a></li>

<li><a href="Cpplint" title="Cpplint">Cpplint</a></li>

<li><a href="FlatBuffers" title="FlatBuffers">FlatBuffers</a></li>

<li><a href="Flutter_(software)" title="Flutter (software)">Flutter</a></li>

<li><a href="Ganeti" title="Ganeti">Ganeti</a></li>

<li><a href="Gears_(software)" title="Gears (software)">Gears</a></li>

<li><a href="Gerrit_(software)" title="Gerrit (software)">Gerrit</a></li>

<li><a href="Google_Guava" title="Google Guava">Guava</a></li>

<li><a href="Guetzli" title="Guetzli">Guetzli</a></li>

<li><a href="Google_Guice" title="Google Guice">Guice</a></li>

<li><a href="GVisor" title="GVisor">gVisor</a></li>

<li><a href="Kubernetes" title="Kubernetes">Kubernetes</a></li>

<li><a href="LevelDB" title="LevelDB">LevelDB</a></li>

<li><a href="Libvpx" title="Libvpx">libvpx</a></li>

<li><a href="Lighthouse_(software)" title="Lighthouse (software)">Lighthouse</a></li>

<li><a href="Namebench" title="Namebench">Namebench</a></li>

<li><a href="Nomulus" title="Nomulus">Nomulus</a></li>

<li><a href="OR-Tools" title="OR-Tools">OR-Tools</a></li>

<li><a href="Polymer_(library)" title="Polymer (library)">Polymer</a></li>

<li><a href="Protocol_Buffers" title="Protocol Buffers">Protocol Buffers</a></li>

</div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%">Operating systems</th><td class="navbox-list-with-group navbox-list navbox-even" style="width:100%;padding:0"><div style="padding:0 0.25em">

<ul><li><a href="Android_(operating_system)" title="Android (operating system)">Android</a></li>

<li><a href="ChromiumOS" title="ChromiumOS">ChromiumOS</a></li>

<li><a href="Fuchsia_(operating_system)" title="Fuchsia (operating system)">Fuchsia</a></li>

<li><a href="GLinux" title="GLinux">gLinux</a></li>

<li><a href="Goobuntu" title="Goobuntu">Goobuntu</a></li></ul>

</div></td></tr></tbody></table><div></div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%">Related</th><td class="navbox-list-with-group navbox-list navbox-odd hlist" style="width:100%;padding:0"><div style="padding:0 0.25em">

<li><i><a href="Google_LLC_v._Oracle_America%2C_Inc." title="Google LLC v. Oracle America, Inc.">Google LLC v. Oracle America, Inc.</a></i></li>

<li><a href="Open_Source_Security_Foundation" title="Open Source Security Foundation">Open Source Security Foundation</a></li>

<li><a href="Google_Summer_of_Code" title="Google Summer of Code">Summer of Code</a></li></ul>

</div></td></tr></tbody></table></div></div><div><div class="zim-footer">

This article is issued from <a class="external text" title="Last edited on 2025-08-03" href="https://en.wikipedia.org/wiki/?title=TensorFlow&oldid=1303997426">Wikipedia</a>. The text is available under <a class="external text" href="https://creativecommons.org/licenses/by-sa/4.0/deed.en">Creative Commons Attribution-Share Alike 4.0</a> unless otherwise noted. Additional terms may apply for the media files.

</div>

</div></div>

</div>

</main>

</div>

</body></html>