Menu
Home
People
Places
Arts
History
Plants & Animals
Science
Life & Culture
Technology
Reference.org
TensorFlow
open-in-new
<h2 id="history">History</h2> <h3>DistBelief</h3> <p>Starting in 2011, Google Brain built DistBelief as a <a href="/facts/Proprietary_software/9zcskxYL">proprietary</a> <a href="/facts/Machine_learning/e0w0XJTu">machine learning</a> system based on <a href="/facts/Deep_learning/JLuwD3ea">deep learning</a> <a href="/facts/Artificial_neural_network/6V1jMlkx">neural networks</a>. Its use grew rapidly across diverse <a href="/facts/Alphabet_Inc./K3QvP6ns">Alphabet</a> companies in both research and commercial applications.<a class="footnote-ref" id="fnref:11" href="#fn:11"><sup>11</sup></a><a class="footnote-ref" id="fnref:12" href="#fn:12"><sup>12</sup></a> Google assigned multiple computer scientists, including <a href="/facts/Jeff_Dean_(computer_scientist)/YIEWyTM4">Jeff Dean</a>, to simplify and <a href="/facts/Code_refactoring/gkw9oVTE">refactor</a> the codebase of DistBelief into a faster, more robust application-grade library, which became TensorFlow.<a class="footnote-ref" id="fnref:13" href="#fn:13"><sup>13</sup></a> In 2009, the team, led by <a href="/facts/Geoffrey_Hinton/HJU6lC2H">Geoffrey Hinton</a>, had implemented generalized <a href="/facts/Backpropagation/lCsIdKHc">backpropagation</a> and other improvements, which allowed generation of <a href="/facts/Neural_network/DDhJTfMc">neural networks</a> with substantially higher accuracy, for instance a 25% reduction in errors in <a href="/facts/Speech_recognition/z7S7Pgk6">speech recognition</a>.<a class="footnote-ref" id="fnref:14" href="#fn:14"><sup>14</sup></a> </p> <h3>TensorFlow</h3> <p>TensorFlow is Google Brain's second-generation system. Version 1.0.0 was released on February 11, 2017.<a class="footnote-ref" id="fnref:15" href="#fn:15"><sup>15</sup></a> While the <a href="/facts/Reference_implementation/k9B97xel">reference implementation</a> runs on single devices, TensorFlow can run on multiple <a href="/facts/Central_processing_unit/Jxp1bqMV">CPUs</a> and <a href="/facts/GPU/PTK1RQVp">GPUs</a> (with optional <a href="/facts/CUDA/fvPpolot">CUDA</a> and <a href="/facts/SYCL/0NXdS7Wg">SYCL</a> extensions for <a href="/facts/General-purpose_computing_on_graphics_processing_units/roBwsPY2">general-purpose computing on graphics processing units</a>).<a class="footnote-ref" id="fnref:16" href="#fn:16"><sup>16</sup></a> TensorFlow is available on 64-bit <a href="/facts/Linux/9FvCKSTq">Linux</a>, <a href="/facts/MacOS/Y93vVpTm">macOS</a>, <a href="/facts/Windows/bwhAhuSL">Windows</a>, and mobile computing platforms including <a href="/facts/Android_(operating_system)/nNyHb0xz">Android</a> and <a href="/facts/IOS/mK5cggH5">iOS</a>.<a class="footnote-ref" id="fnref:17" href="#fn:17"><sup>17</sup></a><a class="footnote-ref" id="fnref:18" href="#fn:18"><sup>18</sup></a> </p><p>Its flexible architecture allows for easy deployment of computation across a variety of platforms (CPUs, GPUs, <a href="/facts/Tensor_processing_unit/aVlg0LFF">TPUs</a>), and from desktops to clusters of servers to mobile and <a href="/facts/Edge_device/YYjW304H">edge devices</a>. </p><p>TensorFlow computations are expressed as <a href="/facts/State_(computer_science)/4Yu8xXHS">stateful</a> <a href="/facts/Dataflow_programming/60IdWpE1">dataflow</a> <a href="/facts/Directed_graph/YBdfQ0um">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="/facts/Tensor/pNjFo5tV">tensors</a></i>.<a class="footnote-ref" id="fnref:19" href="#fn:19"><sup>19</sup></a> During the <a href="/facts/Google_I%2fO/dccHXkGF">Google I/O Conference</a> in June 2016, Jeff Dean stated that 1,500 repositories on <a href="/facts/GitHub/n1hNCsc3">GitHub</a> mentioned TensorFlow, of which only 5 were from Google.<a class="footnote-ref" id="fnref:20" href="#fn:20"><sup>20</sup></a> </p><p>In March 2018, Google announced TensorFlow.js version 1.0 for machine learning in <a href="/facts/JavaScript/XhhIIEsl">JavaScript</a>.<a class="footnote-ref" id="fnref:21" href="#fn:21"><sup>21</sup></a> </p><p>In Jan 2019, Google announced TensorFlow 2.0.<a class="footnote-ref" id="fnref:22" href="#fn:22"><sup>22</sup></a> It became officially available in September 2019.<a class="footnote-ref" id="fnref:23" href="#fn:23"><sup>23</sup></a> </p><p>In May 2019, Google announced TensorFlow Graphics for deep learning in computer graphics.<a class="footnote-ref" id="fnref:24" href="#fn:24"><sup>24</sup></a> </p> <h3>Tensor processing unit (TPU)</h3> <p class="note">Main article: <a href="/facts/Tensor_processing_unit/aVlg0LFF">Tensor processing unit</a></p> <p>In May 2016, Google announced its <a href="/facts/Tensor_processing_unit/aVlg0LFF">Tensor processing unit</a> (TPU), an <a href="/facts/Application-specific_integrated_circuit/YGUXpX50">application-specific integrated circuit</a> (<a href="/facts/Application-specific_integrated_circuit/YGUXpX50">ASIC</a>, a hardware chip) built specifically for machine learning and tailored for TensorFlow. A TPU is a programmable <a href="/facts/AI_accelerator_(computer_hardware)/k0QuXHIb">AI accelerator</a> designed to provide high <a href="/facts/Throughput/6zAUsXqw">throughput</a> of low-precision <a href="/facts/Arithmetic/hvHwkbMV">arithmetic</a> (e.g., <a href="/facts/8-bit/2CkhLNoH">8-bit</a>), and oriented toward using or running models rather than <a href="/facts/Supervised_learning/JlNFNPFt">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="/facts/Order_of_magnitude/cWzRP2dM">order of magnitude</a> better-optimized <a href="/facts/Performance_per_watt/rnXFPlME">performance per watt</a> for machine learning.<a class="footnote-ref" id="fnref:25" href="#fn:25"><sup>25</sup></a> </p><p>In May 2017, Google announced the second-generation, as well as the availability of the TPUs in <a href="/facts/Google_Compute_Engine/tJDHgQke">Google Compute Engine</a>.<a class="footnote-ref" id="fnref:26" href="#fn:26"><sup>26</sup></a> The second-generation TPUs deliver up to 180 <a href="/facts/FLOPS/6zYlH68F">teraflops</a> of performance, and when organized into clusters of 64 TPUs, provide up to 11.5 <a href="/facts/FLOPS/6zYlH68F">petaflops</a>. </p><p>In May 2018, Google announced the third-generation TPUs delivering up to 420 <a href="/facts/FLOPS/6zYlH68F">teraflops</a> of performance and 128 GB high <a href="/facts/Bandwidth_(computing)/lY6Tb4gX">bandwidth</a> memory (HBM). Cloud TPU v3 Pods offer 100+ <a href="/facts/FLOPS/6zYlH68F">petaflops</a> of performance and 32 TB HBM.<a class="footnote-ref" id="fnref:27" href="#fn:27"><sup>27</sup></a> </p><p>In February 2018, Google announced that they were making TPUs available in beta on the <a href="/facts/Google_Cloud_Platform/lPTNk7l6">Google Cloud Platform</a>.<a class="footnote-ref" id="fnref:28" href="#fn:28"><sup>28</sup></a> </p> <h3>Edge TPU</h3> <p>In July 2018, the Edge TPU was announced. Edge TPU is Google's purpose-built <a href="/facts/Application-specific_integrated_circuit/YGUXpX50">ASIC</a> chip designed to run TensorFlow Lite machine learning (ML) models on small client computing devices such as smartphones<a class="footnote-ref" id="fnref:29" href="#fn:29"><sup>29</sup></a> known as <a href="/facts/Edge_computing/4lqr8N6V">edge computing</a>. </p> <h3>TensorFlow Lite</h3> <p>In May 2017, Google announced a software stack specifically for mobile development, TensorFlow Lite.<a class="footnote-ref" id="fnref:30" href="#fn:30"><sup>30</sup></a> 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.<a class="footnote-ref" id="fnref:31" href="#fn:31"><sup>31</sup></a> In May 2019, Google announced that their TensorFlow Lite Micro (also known as TensorFlow Lite for Microcontrollers) and <a href="/facts/Arm_Holdings/jqqppj7b">ARM's</a> uTensor would be merging.<a class="footnote-ref" id="fnref:32" href="#fn:32"><sup>32</sup></a> </p> <h3>TensorFlow 2.0</h3> <p>As TensorFlow's market share among research papers was declining to the advantage of <a href="/facts/PyTorch/4Gv1t13B">PyTorch</a>,<a class="footnote-ref" id="fnref:33" href="#fn:33"><sup>33</sup></a> 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="/facts/Chainer/WN7uuwcz">Chainer</a> and later <a href="/facts/PyTorch/4Gv1t13B">PyTorch</a>.<a class="footnote-ref" id="fnref:34" href="#fn:34"><sup>34</sup></a> 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.<a class="footnote-ref" id="fnref:35" href="#fn:35"><sup>35</sup></a> </p> <h2 id="features">Features</h2> <h3>AutoDifferentiation</h3> <p><a href="/facts/Automatic_differentiation/dQcdhBAM">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="/facts/Backpropagation/lCsIdKHc">backpropagation</a> which require gradients to optimize performance.<a class="footnote-ref" id="fnref:36" href="#fn:36"><sup>36</sup></a> 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.<a class="footnote-ref" id="fnref:37" href="#fn:37"><sup>37</sup></a> </p> <h3>Eager execution</h3> <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.<a class="footnote-ref" id="fnref:38" href="#fn:38"><sup>38</sup></a> 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.<a class="footnote-ref" id="fnref:39" href="#fn:39"><sup>39</sup></a> This execution paradigm is considered to be easier to debug because of its step by step transparency.<a class="footnote-ref" id="fnref:40" href="#fn:40"><sup>40</sup></a> </p> <h3>Distribute</h3> <p>In both eager and graph executions, TensorFlow provides an API for distributing computation across multiple devices with various distribution strategies.<a class="footnote-ref" id="fnref:41" href="#fn:41"><sup>41</sup></a> This <a href="/facts/Distributed_computing/o5nyhqTF">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.<a class="footnote-ref" id="fnref:42" href="#fn:42"><sup>42</sup></a><a class="footnote-ref" id="fnref:43" href="#fn:43"><sup>43</sup></a> </p> <h3>Losses</h3> <p>To train and assess models, TensorFlow provides a set of <a href="/facts/Loss_function/xv5ozuhl">loss functions</a> (also known as <a href="/facts/Mathematical_optimization/oRn8Iv5I">cost functions</a>).<a class="footnote-ref" id="fnref:44" href="#fn:44"><sup>44</sup></a> Some popular examples include <a href="/facts/Mean_squared_error/kz3TR7bv">mean squared error</a> (MSE) and <a href="/facts/Cross_entropy/IG1WD4jb">binary cross entropy</a> (BCE).<a class="footnote-ref" id="fnref:45" href="#fn:45"><sup>45</sup></a> </p> <h3>Metrics</h3> <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="/facts/Precision_and_recall/Jnmmpl8H">Precision, Recall</a>, and <a href="/facts/Jaccard_index/dUurmTet">Intersection-over-Union</a> (IoU).<a class="footnote-ref" id="fnref:46" href="#fn:46"><sup>46</sup></a> </p> <h3>TF.nn</h3> <p>TensorFlow.nn is a module for executing primitive <a href="/facts/Artificial_neural_network/6V1jMlkx">neural network</a> operations on models.<a class="footnote-ref" id="fnref:47" href="#fn:47"><sup>47</sup></a> Some of these operations include variations of <a href="/facts/Convolutional_neural_network/kHEdnmGU">convolutions</a> (1/2/3D, Atrous, depthwise), <a href="/facts/Activation_function/S4NImL6L">activation functions</a> (<a href="/facts/Softmax_function/pvxeWV6L">Softmax</a>, <a href="/facts/Rectifier_(neural_networks)/pwzdU9jF">RELU</a>, GELU, <a href="/facts/Sigmoid_function/lAXu3AwW">Sigmoid</a>, etc.) and their variations, and other operations (<a href="/facts/Max_pooling/kHEdnmGU">max-pooling</a>, bias-add, etc.).<a class="footnote-ref" id="fnref:48" href="#fn:48"><sup>48</sup></a> </p> <h3>Optimizers</h3> <p>TensorFlow offers a set of optimizers for training neural networks, including <a href="/facts/Adam_(optimization_algorithm)/HbcaYqQP">ADAM</a>, <a href="/facts/Adagrad/HbcaYqQP">ADAGRAD</a>, and <a href="/facts/Stochastic_gradient_descent/HbcaYqQP">Stochastic Gradient Descent</a> (SGD).<a class="footnote-ref" id="fnref:49" href="#fn:49"><sup>49</sup></a> When training a model, different optimizers offer different modes of parameter tuning, often affecting a model's convergence and performance.<a class="footnote-ref" id="fnref:50" href="#fn:50"><sup>50</sup></a> </p> <h2 id="usage-and-extensions">Usage and extensions</h2> <h3>TensorFlow</h3> <p>TensorFlow serves as a core platform and library for machine learning. TensorFlow's APIs use <a href="/facts/Keras/oEGGkgN0">Keras</a> to allow users to make their own machine-learning models.<a class="footnote-ref" id="fnref:51" href="#fn:51"><sup>51</sup></a><a class="footnote-ref" id="fnref:52" href="#fn:52"><sup>52</sup></a> 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.<a class="footnote-ref" id="fnref:53" href="#fn:53"><sup>53</sup></a> </p><p>TensorFlow provides a stable <a href="/facts/Python_(programming_language)/YbuGqofa">Python</a> <a href="/facts/API/GMlN4vUr">Application Program Interface</a> (<a href="/facts/API/GMlN4vUr">API</a>),<a class="footnote-ref" id="fnref:54" href="#fn:54"><sup>54</sup></a> as well as APIs without backwards compatibility guarantee for <a href="/facts/JavaScript/XhhIIEsl">Javascript</a>,<a class="footnote-ref" id="fnref:55" href="#fn:55"><sup>55</sup></a> <a href="/facts/C%252B%252B/Et0F2qn9">C++</a>,<a class="footnote-ref" id="fnref:56" href="#fn:56"><sup>56</sup></a> and <a href="/facts/Java_(programming_language)/9ScgFyAL">Java</a>.<a class="footnote-ref" id="fnref:57" href="#fn:57"><sup>57</sup></a><a class="footnote-ref" id="fnref:58" href="#fn:58"><sup>58</sup></a> Third-party language binding packages are also available for <a href="/facts/C_Sharp_(programming_language)/UC2gxeyb">C#</a>,<a class="footnote-ref" id="fnref:59" href="#fn:59"><sup>59</sup></a><a class="footnote-ref" id="fnref:60" href="#fn:60"><sup>60</sup></a> <a href="/facts/Haskell/ydEsHuGy">Haskell</a>,<a class="footnote-ref" id="fnref:61" href="#fn:61"><sup>61</sup></a> <a href="/facts/Julia_(programming_language)/AoB0PJ9C">Julia</a>,<a class="footnote-ref" id="fnref:62" href="#fn:62"><sup>62</sup></a> <a href="/facts/MATLAB/qPjLISCk">MATLAB</a>,<a class="footnote-ref" id="fnref:63" href="#fn:63"><sup>63</sup></a> <a href="/facts/Object_Pascal/cuGkuISv">Object Pascal</a>,<a class="footnote-ref" id="fnref:64" href="#fn:64"><sup>64</sup></a> <a href="/facts/R_(software)/LSrkr8K8">R</a>,<a class="footnote-ref" id="fnref:65" href="#fn:65"><sup>65</sup></a> <a href="/facts/Scala_(programming_language)/ebL8o6AK">Scala</a>,<a class="footnote-ref" id="fnref:66" href="#fn:66"><sup>66</sup></a> <a href="/facts/Rust_(programming_language)/8JNMV19F">Rust</a>,<a class="footnote-ref" id="fnref:67" href="#fn:67"><sup>67</sup></a> <a href="/facts/OCaml/ThBGLND8">OCaml</a>,<a class="footnote-ref" id="fnref:68" href="#fn:68"><sup>68</sup></a> and <a href="/facts/Crystal_(programming_language)/1JgGPFdm">Crystal</a>.<a class="footnote-ref" id="fnref:69" href="#fn:69"><sup>69</sup></a> Bindings that are now archived and unsupported include <a href="/facts/Go_(programming_language)/oWlsmAFJ">Go</a><a class="footnote-ref" id="fnref:70" href="#fn:70"><sup>70</sup></a> and <a href="/facts/Swift_(programming_language)/A7qHQC32">Swift</a>.<a class="footnote-ref" id="fnref:71" href="#fn:71"><sup>71</sup></a> </p> <h3>TensorFlow.js</h3> <p>TensorFlow also has a library for machine learning in JavaScript. Using the provided <a href="/facts/JavaScript/XhhIIEsl">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.<a class="footnote-ref" id="fnref:72" href="#fn:72"><sup>72</sup></a><a class="footnote-ref" id="fnref:73" href="#fn:73"><sup>73</sup></a> </p> <h3>TFLite</h3> <p>TensorFlow Lite has APIs for mobile apps or embedded devices to generate and deploy TensorFlow models.<a class="footnote-ref" id="fnref:74" href="#fn:74"><sup>74</sup></a> These models are compressed and optimized in order to be more efficient and have a higher performance on smaller capacity devices.<a class="footnote-ref" id="fnref:75" href="#fn:75"><sup>75</sup></a> </p><p>TensorFlow Lite uses <a href="/facts/FlatBuffers/QAzSy9wt">FlatBuffers</a> as the data serialization format for network models, eschewing the <a href="/facts/Protocol_Buffers/4Pj3zymo">Protocol Buffers</a> format used by standard TensorFlow models.<a class="footnote-ref" id="fnref:76" href="#fn:76"><sup>76</sup></a> </p> <h3>TFX</h3> <p>TensorFlow Extended (abbrev. TFX) provides numerous components to perform all the operations needed for end-to-end production.<a class="footnote-ref" id="fnref:77" href="#fn:77"><sup>77</sup></a> Components include loading, validating, and transforming data, tuning, training, and evaluating the machine learning model, and pushing the model itself into production.<a class="footnote-ref" id="fnref:78" href="#fn:78"><sup>78</sup></a><a class="footnote-ref" id="fnref:79" href="#fn:79"><sup>79</sup></a> </p> <h3>Integrations</h3> <h4>Numpy</h4> <p>Numpy is one of the most popular <a href="/facts/Python_(programming_language)/YbuGqofa">Python</a> data libraries, and TensorFlow offers integration and compatibility with its data structures.<a class="footnote-ref" id="fnref:80" href="#fn:80"><sup>80</sup></a> Numpy NDarrays, the library's native datatype, are automatically converted to TensorFlow Tensors in TF operations; the same is also true vice versa.<a class="footnote-ref" id="fnref:81" href="#fn:81"><sup>81</sup></a> 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.<a class="footnote-ref" id="fnref:82" href="#fn:82"><sup>82</sup></a> </p> <h3>Extensions</h3> <p>TensorFlow also offers a variety of <a href="/facts/Library_(computing)/xRzL3P7q">libraries</a> and <a href="/facts/Plug-in_(computing)/351Du3Wu">extensions</a> to advance and extend the models and methods used.<a class="footnote-ref" id="fnref:83" href="#fn:83"><sup>83</sup></a> For example, TensorFlow Recommenders and TensorFlow Graphics are <a href="/facts/Library_(computing)/xRzL3P7q">libraries</a> for their respective functional.<a class="footnote-ref" id="fnref:84" href="#fn:84"><sup>84</sup></a> Other add-ons, <a href="/facts/Library_(computing)/xRzL3P7q">libraries</a>, and <a href="/facts/Software_framework/EWasA8sG">frameworks</a> include TensorFlow Model Optimization, TensorFlow Probability, TensorFlow Quantum, and TensorFlow Decision Forests.<a class="footnote-ref" id="fnref:85" href="#fn:85"><sup>85</sup></a><a class="footnote-ref" id="fnref:86" href="#fn:86"><sup>86</sup></a> </p> <h4>Google Colab</h4> <p>Google also released Colaboratory, a TensorFlow Jupyter notebook environment that does not require any setup.<a class="footnote-ref" id="fnref:87" href="#fn:87"><sup>87</sup></a> It runs on Google Cloud and allows users free access to GPUs and the ability to store and share notebooks on <a href="/facts/Google_Drive/mgEjwvIs">Google Drive</a>.<a class="footnote-ref" id="fnref:88" href="#fn:88"><sup>88</sup></a> </p> <h4>Google JAX</h4> <p class="note">Main article: <a href="/facts/Google_JAX/MnxmwXqc">Google JAX</a></p> <p><a href="/facts/Google_JAX/MnxmwXqc">Google JAX</a> is a machine learning <a href="/facts/Software_framework/EWasA8sG">framework</a> for transforming numerical functions.<a class="footnote-ref" id="fnref:89" href="#fn:89"><sup>89</sup></a><a class="footnote-ref" id="fnref:90" href="#fn:90"><sup>90</sup></a><a class="footnote-ref" id="fnref:91" href="#fn:91"><sup>91</sup></a> It is described as bringing together a modified version of <a href="https://github.com/HIPS/autograd">autograd</a> (automatic obtaining of the gradient function through differentiation of a function) and TensorFlow's <a href="https://www.tensorflow.org/xla">XLA</a> (Accelerated Linear Algebra). It is designed to follow the structure and workflow of <a href="/facts/NumPy/T6FnhWWD">NumPy</a> as closely as possible and works with TensorFlow as well as other frameworks such as <a href="/facts/PyTorch/4Gv1t13B">PyTorch</a>. The primary functions of JAX are:<a class="footnote-ref" id="fnref:92" href="#fn:92"><sup>92</sup></a> </p> <ol><li>grad: automatic differentiation</li> <li>jit: compilation</li> <li>vmap: auto-vectorization</li> <li>pmap: SPMD programming</li></ol> <h2 id="applications">Applications</h2> <h3>Medical</h3> <p><a href="/facts/GE_Healthcare/lneN5A1A">GE Healthcare</a> used TensorFlow to increase the speed and accuracy of <a href="/facts/Magnetic_resonance_imaging/Vh9yG9qq">MRIs</a> in identifying specific body parts.<a class="footnote-ref" id="fnref:93" href="#fn:93"><sup>93</sup></a> Google used TensorFlow to create DermAssist, a free mobile application that allows users to take pictures of their skin and identify potential health complications.<a class="footnote-ref" id="fnref:94" href="#fn:94"><sup>94</sup></a> <a href="/facts/Sinovation_Ventures/RbUxDJ1h">Sinovation Ventures</a> used TensorFlow to identify and classify eye diseases from <a href="/facts/Optical_coherence_tomography/CqoqaP2a">optical coherence tomography</a> (OCT) scans.<a class="footnote-ref" id="fnref:95" href="#fn:95"><sup>95</sup></a> </p> <h3>Social media</h3> <p><a href="/facts/Twitter/VWwDNGUm">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.<a class="footnote-ref" id="fnref:96" href="#fn:96"><sup>96</sup></a> Previously, tweets were simply shown in reverse chronological order.<a class="footnote-ref" id="fnref:97" href="#fn:97"><sup>97</sup></a> The photo sharing app <a href="/facts/VSCO/p3QKdWut">VSCO</a> used TensorFlow to help suggest custom filters for photos.<a class="footnote-ref" id="fnref:98" href="#fn:98"><sup>98</sup></a> </p> <h3>Search Engine</h3> <p><a href="/facts/Google/GT9Sugza">Google</a> officially released <a href="/facts/RankBrain/Sus0QK5H">RankBrain</a> on October 26, 2015, backed by TensorFlow.<a class="footnote-ref" id="fnref:99" href="#fn:99"><sup>99</sup></a> </p> <h3>Education</h3> <p>InSpace, a virtual learning platform, used TensorFlow to filter out toxic chat messages in classrooms.<a class="footnote-ref" id="fnref:100" href="#fn:100"><sup>100</sup></a> Liulishuo, an online English learning platform, utilized TensorFlow to create an adaptive curriculum for each student.<a class="footnote-ref" id="fnref:101" href="#fn:101"><sup>101</sup></a> 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.<a class="footnote-ref" id="fnref:102" href="#fn:102"><sup>102</sup></a> </p> <h3>Retail</h3> <p>The e-commerce platform <a href="/facts/Carousell_(company)/2jn8tPGj">Carousell</a> used TensorFlow to provide personalized recommendations for customers.<a class="footnote-ref" id="fnref:103" href="#fn:103"><sup>103</sup></a> The cosmetics company ModiFace used TensorFlow to create an augmented reality experience for customers to test various shades of make-up on their face.<a class="footnote-ref" id="fnref:104" href="#fn:104"><sup>104</sup></a> </p> <h3>Research</h3> <p>TensorFlow is the foundation for the automated <a href="/facts/Image_captioning/8V2cAfwG">image-captioning</a> software <a href="/facts/DeepDream/7fxAFXUh">DeepDream</a>.<a class="footnote-ref" id="fnref:105" href="#fn:105"><sup>105</sup></a> </p> <h2 id="see-also">See also</h2> <ul> <li>Free and open-source software portal</li></ul> <ul><li><a href="/facts/Comparison_of_deep_learning_software/NJypbDKA">Comparison of deep learning software</a></li> <li><a href="/facts/Differentiable_programming/eH8fj5z1">Differentiable programming</a></li> <li><a href="/facts/Keras/oEGGkgN0">Keras</a></li></ul> <h2 id="further-reading">Further reading</h2> <ul><li>Moroney, Laurence (October 1, 2020). <a href="https://www.oreilly.com/library/view/ai-and-machine/9781492078180/"><i>AI and Machine Learning for Coders</i></a> (1st ed.). <a href="/facts/O%2527Reilly_Media/Fr3Kv7sm">O'Reilly Media</a>. p. 365. <a href="/facts/ISBN_(identifier)/15AdSPa9">ISBN</a> 9781492078197. <a 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. Retrieved December 21, 2020.</li> <li>Géron, Aurélien (October 15, 2019). <a 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="/facts/O%2527Reilly_Media/Fr3Kv7sm">O'Reilly Media</a>. p. 856. <a href="/facts/ISBN_(identifier)/15AdSPa9">ISBN</a> 9781492032632. <a 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. Retrieved November 25, 2019.</li> <li>Ramsundar, Bharath; Zadeh, Reza Bosagh (March 23, 2018). <a href="https://www.oreilly.com/library/view/tensorflow-for-deep/9781491980446/"><i>TensorFlow for Deep Learning</i></a> (1st ed.). <a href="/facts/O%2527Reilly_Media/Fr3Kv7sm">O'Reilly Media</a>. p. 256. <a href="/facts/ISBN_(identifier)/15AdSPa9">ISBN</a> 9781491980446. <a 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. Retrieved November 25, 2019.</li> <li>Hope, Tom; Resheff, Yehezkel S.; Lieder, Itay (August 27, 2017). <a 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="/facts/O%2527Reilly_Media/Fr3Kv7sm">O'Reilly Media</a>. p. 242. <a href="/facts/ISBN_(identifier)/15AdSPa9">ISBN</a> 9781491978504. <a 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. Retrieved November 25, 2019.</li> <li>Shukla, Nishant (February 12, 2018). <i>Machine Learning with TensorFlow</i> (1st ed.). <a href="/facts/Manning_Publications/opB29j1b">Manning Publications</a>. p. 272. <a href="/facts/ISBN_(identifier)/15AdSPa9">ISBN</a> 9781617293870.</li></ul> <h2 id="external-links">External links</h2> <ul><li><a href="http://www.tensorflow.org">Official website</a></li> <li><a href="https://www.oreilly.com/library/view/learning-tensorflowjs/9781492090786/">Learning TensorFlow.js Book (ENG)</a></li></ul> <h2 id="references">References</h2> <ol> <li id="fn:1"><p>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). TensorFlow: A System for Large-Scale Machine Learning (PDF). Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI ’16). arXiv:1605.08695. Archived (PDF) from the original on December 12, 2020. Retrieved October 26, 2020. <a href="https://www.usenix.org/system/files/conference/osdi16/osdi16-abadi.pdf" target="_blank">https://www.usenix.org/system/files/conference/osdi16/osdi16-abadi.pdf</a> <a href="#fnref:1" class="footnote-back-ref">↩</a></p></li> <li id="fn:2"><p>TensorFlow: Open source machine learning. Google. 2015. Archived from the original on November 11, 2021. "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 <a href="https://www.youtube.com/watch?v=oZikw5k_2FM" target="_blank">https://www.youtube.com/watch?v=oZikw5k_2FM</a> <a href="#fnref:2" class="footnote-back-ref">↩</a></p></li> <li id="fn:3"><p>"Top 30 Open Source Projects". Open Source Project Velocity by CNCF. Archived from the original on September 3, 2023. Retrieved October 12, 2023. <a href="https://github.com/cncf/velocity" target="_blank">https://github.com/cncf/velocity</a> <a href="#fnref:3" class="footnote-back-ref">↩</a></p></li> <li id="fn:4"><p>Video clip by Google about TensorFlow 2015 at minute 0:15/2:17 - TensorFlow: Open source machine learning. Google. 2015. Archived from the original on November 11, 2021. <a href="https://www.youtube.com/watch?v=oZikw5k_2FM" target="_blank">https://www.youtube.com/watch?v=oZikw5k_2FM</a> <a href="#fnref:4" class="footnote-back-ref">↩</a></p></li> <li id="fn:5"><p>Video clip by Google about TensorFlow 2015 at minute 0:26/2:17 - TensorFlow: Open source machine learning. Google. 2015. Archived from the original on November 11, 2021. <a href="https://www.youtube.com/watch?v=oZikw5k_2FM" target="_blank">https://www.youtube.com/watch?v=oZikw5k_2FM</a> <a href="#fnref:5" class="footnote-back-ref">↩</a></p></li> <li id="fn:6"><p>Dean et al 2015, p. 2 - Dean, Jeff; Monga, Rajat; et al. (November 9, 2015). "TensorFlow: Large-scale machine learning on heterogeneous systems" (PDF). TensorFlow.org. Google Research. Archived (PDF) from the original on November 20, 2015. Retrieved November 10, 2015. <a href="http://download.tensorflow.org/paper/whitepaper2015.pdf" target="_blank">http://download.tensorflow.org/paper/whitepaper2015.pdf</a> <a href="#fnref:6" class="footnote-back-ref">↩</a></p></li> <li id="fn:7"><p>"Credits". TensorFlow.org. Archived from the original on November 17, 2015. Retrieved November 10, 2015. <a href="https://tensorflow.org/about" target="_blank">https://tensorflow.org/about</a> <a href="#fnref:7" class="footnote-back-ref">↩</a></p></li> <li id="fn:8"><p>Metz, Cade (November 9, 2015). "Google Just Open Sourced TensorFlow, Its Artificial Intelligence Engine". Wired. Archived from the original on November 9, 2015. Retrieved November 10, 2015. <a href="https://www.wired.com/2015/11/google-open-sources-its-artificial-intelligence-engine/" target="_blank">https://www.wired.com/2015/11/google-open-sources-its-artificial-intelligence-engine/</a> <a href="#fnref:8" class="footnote-back-ref">↩</a></p></li> <li id="fn:9"><p>TensorFlow (September 30, 2019). "TensorFlow 2.0 is now available!". Medium. Archived from the original on October 7, 2019. Retrieved November 24, 2019. <a href="https://medium.com/tensorflow/tensorflow-2-0-is-now-available-57d706c2a9ab" target="_blank">https://medium.com/tensorflow/tensorflow-2-0-is-now-available-57d706c2a9ab</a> <a href="#fnref:9" class="footnote-back-ref">↩</a></p></li> <li id="fn:10"><p>"API Documentation". Archived from the original on November 16, 2015. Retrieved June 27, 2018., <a href="https://www.tensorflow.org/api_docs/" target="_blank">https://www.tensorflow.org/api_docs/</a> <a href="#fnref:10" class="footnote-back-ref">↩</a></p></li> <li id="fn:11"><p>Dean, Jeff; Monga, Rajat; et al. (November 9, 2015). "TensorFlow: Large-scale machine learning on heterogeneous systems" (PDF). TensorFlow.org. Google Research. Archived (PDF) from the original on November 20, 2015. Retrieved November 10, 2015. <a href="/wiki/Jeff_Dean_(computer_scientist)" target="_blank">/wiki/Jeff_Dean_(computer_scientist)</a> <a href="#fnref:11" class="footnote-back-ref">↩</a></p></li> <li id="fn:12"><p>Perez, Sarah (November 9, 2015). "Google Open-Sources The Machine Learning Tech Behind Google Photos Search, Smart Reply And More". TechCrunch. Archived from the original on November 9, 2015. Retrieved November 11, 2015. <a href="https://techcrunch.com/2015/11/09/google-open-sources-the-machine-learning-tech-behind-google-photos-search-smart-reply-and-more/" target="_blank">https://techcrunch.com/2015/11/09/google-open-sources-the-machine-learning-tech-behind-google-photos-search-smart-reply-and-more/</a> <a href="#fnref:12" class="footnote-back-ref">↩</a></p></li> <li id="fn:13"><p>Oremus, Will (November 9, 2015). "What Is TensorFlow, and Why Is Google So Excited About It?". Slate. Archived from the original on November 10, 2015. Retrieved November 11, 2015. <a 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" target="_blank">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</a> <a href="#fnref:13" class="footnote-back-ref">↩</a></p></li> <li id="fn:14"><p>Ward-Bailey, Jeff (November 25, 2015). "Google chairman: We're making 'real progress' on artificial intelligence". CSMonitor. Archived from the original on September 16, 2015. Retrieved November 25, 2015. <a href="https://www.csmonitor.com/Technology/2015/0914/Google-chairman-We-re-making-real-progress-on-artificial-intelligence" target="_blank">https://www.csmonitor.com/Technology/2015/0914/Google-chairman-We-re-making-real-progress-on-artificial-intelligence</a> <a href="#fnref:14" class="footnote-back-ref">↩</a></p></li> <li id="fn:15"><p>TensorFlow Developers (2022). "Tensorflow Release 1.0.0". GitHub. doi:10.5281/zenodo.4724125. Archived from the original on February 27, 2021. Retrieved July 24, 2017. <a href="https://github.com/tensorflow/tensorflow/blob/07bb8ea2379bd459832b23951fb20ec47f3fdbd4/RELEASE.md" target="_blank">https://github.com/tensorflow/tensorflow/blob/07bb8ea2379bd459832b23951fb20ec47f3fdbd4/RELEASE.md</a> <a href="#fnref:15" class="footnote-back-ref">↩</a></p></li> <li id="fn:16"><p>Metz, Cade (November 10, 2015). "TensorFlow, Google's Open Source AI, Points to a Fast-Changing Hardware World". Wired. Archived from the original on November 11, 2015. Retrieved November 11, 2015. <a href="https://www.wired.com/2015/11/googles-open-source-ai-tensorflow-signals-fast-changing-hardware-world/" target="_blank">https://www.wired.com/2015/11/googles-open-source-ai-tensorflow-signals-fast-changing-hardware-world/</a> <a href="#fnref:16" class="footnote-back-ref">↩</a></p></li> <li id="fn:17"><p>Kudale, Aniket Eknath (June 8, 2020). "Building a Facial Expression Recognition App Using TensorFlow.js". Open Source For U. Archived from the original on October 11, 2024. Retrieved April 19, 2025. <a href="https://www.opensourceforu.com/2020/06/building-a-facial-expression-recognition-app-using-tensorflow-js/" target="_blank">https://www.opensourceforu.com/2020/06/building-a-facial-expression-recognition-app-using-tensorflow-js/</a> <a href="#fnref:17" class="footnote-back-ref">↩</a></p></li> <li id="fn:18"><p>MSV, Janakiram (February 24, 2021). "The Ultimate Guide to Machine Learning Frameworks". The New Stack. Archived from the original on December 24, 2024. Retrieved April 19, 2025. <a href="https://thenewstack.io/the-ultimate-guide-to-machine-learning-frameworks/" target="_blank">https://thenewstack.io/the-ultimate-guide-to-machine-learning-frameworks/</a> <a href="#fnref:18" class="footnote-back-ref">↩</a></p></li> <li id="fn:19"><p>"Introduction to tensors". tensorflow.org. Archived from the original on May 26, 2024. Retrieved March 3, 2024. <a href="https://www.tensorflow.org/guide/tensor" target="_blank">https://www.tensorflow.org/guide/tensor</a> <a href="#fnref:19" class="footnote-back-ref">↩</a></p></li> <li id="fn:20"><p>Machine Learning: Google I/O 2016 Minute 07:30/44:44 . Archived December 21, 2016, at the Wayback Machine. Retrieved June 5, 2016. <a href="https://www.youtube.com/watch?v=Rnm83GqgqPE" target="_blank">https://www.youtube.com/watch?v=Rnm83GqgqPE</a> <a href="#fnref:20" class="footnote-back-ref">↩</a></p></li> <li id="fn:21"><p>TensorFlow (March 30, 2018). "Introducing TensorFlow.js: Machine Learning in Javascript". Medium. Archived from the original on March 30, 2018. Retrieved May 24, 2019. <a href="https://medium.com/tensorflow/introducing-tensorflow-js-machine-learning-in-javascript-bf3eab376db" target="_blank">https://medium.com/tensorflow/introducing-tensorflow-js-machine-learning-in-javascript-bf3eab376db</a> <a href="#fnref:21" class="footnote-back-ref">↩</a></p></li> <li id="fn:22"><p>TensorFlow (January 14, 2019). "What's coming in TensorFlow 2.0". Medium. Archived from the original on January 14, 2019. Retrieved May 24, 2019. <a href="https://medium.com/tensorflow/whats-coming-in-tensorflow-2-0-d3663832e9b8" target="_blank">https://medium.com/tensorflow/whats-coming-in-tensorflow-2-0-d3663832e9b8</a> <a href="#fnref:22" class="footnote-back-ref">↩</a></p></li> <li id="fn:23"><p>TensorFlow (September 30, 2019). "TensorFlow 2.0 is now available!". Medium. Archived from the original on October 7, 2019. Retrieved November 24, 2019. <a href="https://medium.com/tensorflow/tensorflow-2-0-is-now-available-57d706c2a9ab" target="_blank">https://medium.com/tensorflow/tensorflow-2-0-is-now-available-57d706c2a9ab</a> <a href="#fnref:23" class="footnote-back-ref">↩</a></p></li> <li id="fn:24"><p>TensorFlow (May 9, 2019). "Introducing TensorFlow Graphics: Computer Graphics Meets Deep Learning". Medium. Archived from the original on May 9, 2019. Retrieved May 24, 2019. <a href="https://medium.com/tensorflow/introducing-tensorflow-graphics-computer-graphics-meets-deep-learning-c8e3877b7668" target="_blank">https://medium.com/tensorflow/introducing-tensorflow-graphics-computer-graphics-meets-deep-learning-c8e3877b7668</a> <a href="#fnref:24" class="footnote-back-ref">↩</a></p></li> <li id="fn:25"><p>Jouppi, Norm. "Google supercharges machine learning tasks with TPU custom chip". Google Cloud Platform Blog. Archived from the original on May 18, 2016. Retrieved May 19, 2016. <a href="/wiki/Norman_Jouppi" target="_blank">/wiki/Norman_Jouppi</a> <a href="#fnref:25" class="footnote-back-ref">↩</a></p></li> <li id="fn:26"><p>"Build and train machine learning models on our new Google Cloud TPUs". Google. May 17, 2017. Archived from the original on May 17, 2017. Retrieved May 18, 2017. <a href="https://www.blog.google/topics/google-cloud/google-cloud-offer-tpus-machine-learning/" target="_blank">https://www.blog.google/topics/google-cloud/google-cloud-offer-tpus-machine-learning/</a> <a href="#fnref:26" class="footnote-back-ref">↩</a></p></li> <li id="fn:27"><p>"Cloud TPU". Google Cloud. Archived from the original on May 17, 2017. Retrieved May 24, 2019. <a href="https://cloud.google.com/tpu/" target="_blank">https://cloud.google.com/tpu/</a> <a href="#fnref:27" class="footnote-back-ref">↩</a></p></li> <li id="fn:28"><p>"Cloud TPU machine learning accelerators now available in beta". Google Cloud Platform Blog. Archived from the original on February 12, 2018. Retrieved February 12, 2018. <a href="https://cloudplatform.googleblog.com/2018/02/Cloud-TPU-machine-learning-accelerators-now-available-in-beta.html" target="_blank">https://cloudplatform.googleblog.com/2018/02/Cloud-TPU-machine-learning-accelerators-now-available-in-beta.html</a> <a href="#fnref:28" class="footnote-back-ref">↩</a></p></li> <li id="fn:29"><p>Kundu, Kishalaya (July 26, 2018). "Google Announces Edge TPU, Cloud IoT Edge at Cloud Next 2018". Beebom. Archived from the original on May 26, 2024. Retrieved February 2, 2019. <a href="https://beebom.com/google-announces-edge-tpu-cloud-iot-edge-at-cloud-next-2018/" target="_blank">https://beebom.com/google-announces-edge-tpu-cloud-iot-edge-at-cloud-next-2018/</a> <a href="#fnref:29" class="footnote-back-ref">↩</a></p></li> <li id="fn:30"><p>"Google's new machine learning framework is going to put more AI on your phone". May 17, 2017. Archived from the original on May 17, 2017. Retrieved May 19, 2017. <a href="https://www.theverge.com/2017/5/17/15645908/google-ai-tensorflowlite-machine-learning-announcement-io-2017" target="_blank">https://www.theverge.com/2017/5/17/15645908/google-ai-tensorflowlite-machine-learning-announcement-io-2017</a> <a href="#fnref:30" class="footnote-back-ref">↩</a></p></li> <li id="fn:31"><p>TensorFlow (January 16, 2019). "TensorFlow Lite Now Faster with Mobile GPUs (Developer Preview)". Medium. Archived from the original on January 16, 2019. Retrieved May 24, 2019. <a href="https://medium.com/tensorflow/tensorflow-lite-now-faster-with-mobile-gpus-developer-preview-e15797e6dee7" target="_blank">https://medium.com/tensorflow/tensorflow-lite-now-faster-with-mobile-gpus-developer-preview-e15797e6dee7</a> <a href="#fnref:31" class="footnote-back-ref">↩</a></p></li> <li id="fn:32"><p>"uTensor and Tensor Flow Announcement | Mbed". os.mbed.com. Archived from the original on May 9, 2019. Retrieved May 24, 2019. <a href="https://os.mbed.com/blog/entry/uTensor-and-Tensor-Flow-Announcement/" target="_blank">https://os.mbed.com/blog/entry/uTensor-and-Tensor-Flow-Announcement/</a> <a href="#fnref:32" class="footnote-back-ref">↩</a></p></li> <li id="fn:33"><p>He, Horace (October 10, 2019). "The State of Machine Learning Frameworks in 2019". The Gradient. Archived from the original on October 10, 2019. Retrieved May 22, 2020. <a href="https://thegradient.pub/state-of-ml-frameworks-2019-pytorch-dominates-research-tensorflow-dominates-industry/" target="_blank">https://thegradient.pub/state-of-ml-frameworks-2019-pytorch-dominates-research-tensorflow-dominates-industry/</a> <a href="#fnref:33" class="footnote-back-ref">↩</a></p></li> <li id="fn:34"><p>He, Horace (October 10, 2019). "The State of Machine Learning Frameworks in 2019". The Gradient. Archived from the original on October 10, 2019. Retrieved May 22, 2020. <a href="https://thegradient.pub/state-of-ml-frameworks-2019-pytorch-dominates-research-tensorflow-dominates-industry/" target="_blank">https://thegradient.pub/state-of-ml-frameworks-2019-pytorch-dominates-research-tensorflow-dominates-industry/</a> <a href="#fnref:34" class="footnote-back-ref">↩</a></p></li> <li id="fn:35"><p>Ciaramella, Alberto; Ciaramella, Marco (July 2024). Introduction to Artificial Intelligence: from data analysis to generative AI. Intellisemantic Editions. ISBN 9788894787603. <a href="9788894787603" target="_blank">9788894787603</a> <a href="#fnref:35" class="footnote-back-ref">↩</a></p></li> <li id="fn:36"><p>"Introduction to gradients and automatic differentiation". TensorFlow. Archived from the original on October 28, 2021. Retrieved November 4, 2021. <a href="https://www.tensorflow.org/guide/autodiff" target="_blank">https://www.tensorflow.org/guide/autodiff</a> <a href="#fnref:36" class="footnote-back-ref">↩</a></p></li> <li id="fn:37"><p>"Introduction to gradients and automatic differentiation". TensorFlow. Archived from the original on October 28, 2021. Retrieved November 4, 2021. <a href="https://www.tensorflow.org/guide/autodiff" target="_blank">https://www.tensorflow.org/guide/autodiff</a> <a href="#fnref:37" class="footnote-back-ref">↩</a></p></li> <li id="fn:38"><p>"Eager execution | TensorFlow Core". TensorFlow. Archived from the original on November 4, 2021. Retrieved November 4, 2021. <a href="https://www.tensorflow.org/guide/eager" target="_blank">https://www.tensorflow.org/guide/eager</a> <a href="#fnref:38" class="footnote-back-ref">↩</a></p></li> <li id="fn:39"><p>"Eager execution | TensorFlow Core". TensorFlow. Archived from the original on November 4, 2021. Retrieved November 4, 2021. <a href="https://www.tensorflow.org/guide/eager" target="_blank">https://www.tensorflow.org/guide/eager</a> <a href="#fnref:39" class="footnote-back-ref">↩</a></p></li> <li id="fn:40"><p>"Eager execution | TensorFlow Core". TensorFlow. Archived from the original on November 4, 2021. Retrieved November 4, 2021. <a href="https://www.tensorflow.org/guide/eager" target="_blank">https://www.tensorflow.org/guide/eager</a> <a href="#fnref:40" class="footnote-back-ref">↩</a></p></li> <li id="fn:41"><p>"Module: tf.distribute | TensorFlow Core v2.6.1". TensorFlow. Archived from the original on May 26, 2024. Retrieved November 4, 2021. <a href="https://www.tensorflow.org/api_docs/python/tf/distribute" target="_blank">https://www.tensorflow.org/api_docs/python/tf/distribute</a> <a href="#fnref:41" class="footnote-back-ref">↩</a></p></li> <li id="fn:42"><p>"Module: tf.distribute | TensorFlow Core v2.6.1". TensorFlow. Archived from the original on May 26, 2024. Retrieved November 4, 2021. <a href="https://www.tensorflow.org/api_docs/python/tf/distribute" target="_blank">https://www.tensorflow.org/api_docs/python/tf/distribute</a> <a href="#fnref:42" class="footnote-back-ref">↩</a></p></li> <li id="fn:43"><p>Sigeru., Omatu (2014). Distributed Computing and Artificial Intelligence, 11th International Conference. Springer International Publishing. ISBN 978-3-319-07593-8. OCLC 980886715. Archived from the original on May 26, 2024. Retrieved November 4, 2021. <a href="978-3-319-07593-8" target="_blank">978-3-319-07593-8</a> <a href="#fnref:43" class="footnote-back-ref">↩</a></p></li> <li id="fn:44"><p>"Module: tf.losses | TensorFlow Core v2.6.1". TensorFlow. Archived from the original on October 27, 2021. Retrieved November 4, 2021. <a href="https://www.tensorflow.org/api_docs/python/tf/losses" target="_blank">https://www.tensorflow.org/api_docs/python/tf/losses</a> <a href="#fnref:44" class="footnote-back-ref">↩</a></p></li> <li id="fn:45"><p>"Module: tf.losses | TensorFlow Core v2.6.1". TensorFlow. Archived from the original on October 27, 2021. Retrieved November 4, 2021. <a href="https://www.tensorflow.org/api_docs/python/tf/losses" target="_blank">https://www.tensorflow.org/api_docs/python/tf/losses</a> <a href="#fnref:45" class="footnote-back-ref">↩</a></p></li> <li id="fn:46"><p>"Module: tf.metrics | TensorFlow Core v2.6.1". TensorFlow. Archived from the original on November 4, 2021. Retrieved November 4, 2021. <a href="https://www.tensorflow.org/api_docs/python/tf/metrics" target="_blank">https://www.tensorflow.org/api_docs/python/tf/metrics</a> <a href="#fnref:46" class="footnote-back-ref">↩</a></p></li> <li id="fn:47"><p>"Module: tf.nn | TensorFlow Core v2.7.0". TensorFlow. Archived from the original on May 26, 2024. Retrieved November 6, 2021. <a href="https://www.tensorflow.org/api_docs/python/tf/nn" target="_blank">https://www.tensorflow.org/api_docs/python/tf/nn</a> <a href="#fnref:47" class="footnote-back-ref">↩</a></p></li> <li id="fn:48"><p>"Module: tf.nn | TensorFlow Core v2.7.0". TensorFlow. Archived from the original on May 26, 2024. Retrieved November 6, 2021. <a href="https://www.tensorflow.org/api_docs/python/tf/nn" target="_blank">https://www.tensorflow.org/api_docs/python/tf/nn</a> <a href="#fnref:48" class="footnote-back-ref">↩</a></p></li> <li id="fn:49"><p>"Module: tf.optimizers | TensorFlow Core v2.7.0". TensorFlow. Archived from the original on October 30, 2021. Retrieved November 6, 2021. <a href="https://www.tensorflow.org/api_docs/python/tf/optimizers" target="_blank">https://www.tensorflow.org/api_docs/python/tf/optimizers</a> <a href="#fnref:49" class="footnote-back-ref">↩</a></p></li> <li id="fn:50"><p>Dogo, E. M.; Afolabi, O. J.; Nwulu, N. I.; Twala, B.; Aigbavboa, C. O. (December 2018). "A Comparative Analysis of Gradient Descent-Based Optimization Algorithms on Convolutional Neural Networks". 2018 International Conference on Computational Techniques, Electronics and Mechanical Systems (CTEMS). pp. 92–99. doi:10.1109/CTEMS.2018.8769211. ISBN 978-1-5386-7709-4. S2CID 198931032. Archived from the original on May 26, 2024. Retrieved July 25, 2023. <a href="978-1-5386-7709-4" target="_blank">978-1-5386-7709-4</a> <a href="#fnref:50" class="footnote-back-ref">↩</a></p></li> <li id="fn:51"><p>Ciaramella, Alberto; Ciaramella, Marco (July 2024). Introduction to Artificial Intelligence: from data analysis to generative AI. Intellisemantic Editions. ISBN 9788894787603. <a href="9788894787603" target="_blank">9788894787603</a> <a href="#fnref:51" class="footnote-back-ref">↩</a></p></li> <li id="fn:52"><p>"TensorFlow Core | Machine Learning for Beginners and Experts". TensorFlow. Archived from the original on January 20, 2023. Retrieved November 4, 2021. <a href="https://www.tensorflow.org/overview" target="_blank">https://www.tensorflow.org/overview</a> <a href="#fnref:52" class="footnote-back-ref">↩</a></p></li> <li id="fn:53"><p>"Introduction to TensorFlow". TensorFlow. Archived from the original on January 20, 2023. Retrieved October 28, 2021. <a href="https://www.tensorflow.org/learn" target="_blank">https://www.tensorflow.org/learn</a> <a href="#fnref:53" class="footnote-back-ref">↩</a></p></li> <li id="fn:54"><p>"All symbols in TensorFlow 2 | TensorFlow Core v2.7.0". TensorFlow. Archived from the original on November 6, 2021. Retrieved November 6, 2021. <a href="https://www.tensorflow.org/api_docs/python/tf/all_symbols" target="_blank">https://www.tensorflow.org/api_docs/python/tf/all_symbols</a> <a href="#fnref:54" class="footnote-back-ref">↩</a></p></li> <li id="fn:55"><p>"TensorFlow.js". js.tensorflow.org. Archived from the original on May 26, 2024. Retrieved November 6, 2021. <a href="https://js.tensorflow.org/" target="_blank">https://js.tensorflow.org/</a> <a href="#fnref:55" class="footnote-back-ref">↩</a></p></li> <li id="fn:56"><p>"TensorFlow C++ API Reference | TensorFlow Core v2.7.0". TensorFlow. Archived from the original on January 20, 2023. Retrieved November 6, 2021. <a href="https://www.tensorflow.org/api_docs/cc" target="_blank">https://www.tensorflow.org/api_docs/cc</a> <a href="#fnref:56" class="footnote-back-ref">↩</a></p></li> <li id="fn:57"><p>"org.tensorflow | Java". TensorFlow. Archived from the original on November 6, 2021. Retrieved November 6, 2021. <a href="https://www.tensorflow.org/api_docs/java/org/tensorflow/package-summary" target="_blank">https://www.tensorflow.org/api_docs/java/org/tensorflow/package-summary</a> <a href="#fnref:57" class="footnote-back-ref">↩</a></p></li> <li id="fn:58"><p>"API Documentation". Archived from the original on November 16, 2015. Retrieved June 27, 2018., <a href="https://www.tensorflow.org/api_docs/" target="_blank">https://www.tensorflow.org/api_docs/</a> <a href="#fnref:58" class="footnote-back-ref">↩</a></p></li> <li id="fn:59"><p>Icaza, Miguel de (February 17, 2018). "TensorFlowSharp: TensorFlow API for .NET languages". GitHub. Archived from the original on July 24, 2017. Retrieved February 18, 2018. <a href="https://github.com/migueldeicaza/TensorFlowSharp" target="_blank">https://github.com/migueldeicaza/TensorFlowSharp</a> <a href="#fnref:59" class="footnote-back-ref">↩</a></p></li> <li id="fn:60"><p>Chen, Haiping (December 11, 2018). "TensorFlow.NET: .NET Standard bindings for TensorFlow". GitHub. Archived from the original on July 12, 2019. Retrieved December 11, 2018. <a href="https://github.com/SciSharp/TensorFlow.NET" target="_blank">https://github.com/SciSharp/TensorFlow.NET</a> <a href="#fnref:60" class="footnote-back-ref">↩</a></p></li> <li id="fn:61"><p>"haskell: Haskell bindings for TensorFlow". tensorflow. February 17, 2018. Archived from the original on July 24, 2017. Retrieved February 18, 2018. <a href="https://github.com/tensorflow/haskell" target="_blank">https://github.com/tensorflow/haskell</a> <a href="#fnref:61" class="footnote-back-ref">↩</a></p></li> <li id="fn:62"><p>Malmaud, Jon (August 12, 2019). "A Julia wrapper for TensorFlow". GitHub. Archived from the original on July 24, 2017. Retrieved August 14, 2019. operations like sin, * (matrix multiplication), .* (element-wise multiplication), etc [..]. Compare to Python, which requires learning specialized namespaced functions like tf.matmul. <a href="https://github.com/malmaud/TensorFlow.jl" target="_blank">https://github.com/malmaud/TensorFlow.jl</a> <a href="#fnref:62" class="footnote-back-ref">↩</a></p></li> <li id="fn:63"><p>"A MATLAB wrapper for TensorFlow Core". GitHub. November 3, 2019. Archived from the original on September 14, 2020. Retrieved February 13, 2020. <a href="https://github.com/asteinh/tensorflow.m" target="_blank">https://github.com/asteinh/tensorflow.m</a> <a href="#fnref:63" class="footnote-back-ref">↩</a></p></li> <li id="fn:64"><p>"Use TensorFlow from Pascal (FreePascal, Lazarus, etc.)". GitHub. January 19, 2023. Archived from the original on January 20, 2023. Retrieved January 20, 2023. <a href="https://github.com/zsoltszakaly/tensorflowforpascal" target="_blank">https://github.com/zsoltszakaly/tensorflowforpascal</a> <a href="#fnref:64" class="footnote-back-ref">↩</a></p></li> <li id="fn:65"><p>"tensorflow: TensorFlow for R". RStudio. February 17, 2018. Archived from the original on January 4, 2017. Retrieved February 18, 2018. <a href="https://github.com/rstudio/tensorflow" target="_blank">https://github.com/rstudio/tensorflow</a> <a href="#fnref:65" class="footnote-back-ref">↩</a></p></li> <li id="fn:66"><p>Platanios, Anthony (February 17, 2018). "tensorflow_scala: TensorFlow API for the Scala Programming Language". GitHub. Archived from the original on February 18, 2019. Retrieved February 18, 2018. <a href="https://github.com/eaplatanios/tensorflow_scala" target="_blank">https://github.com/eaplatanios/tensorflow_scala</a> <a href="#fnref:66" class="footnote-back-ref">↩</a></p></li> <li id="fn:67"><p>"rust: Rust language bindings for TensorFlow". tensorflow. February 17, 2018. Archived from the original on July 24, 2017. Retrieved February 18, 2018. <a href="https://github.com/tensorflow/rust" target="_blank">https://github.com/tensorflow/rust</a> <a href="#fnref:67" class="footnote-back-ref">↩</a></p></li> <li id="fn:68"><p>Mazare, Laurent (February 16, 2018). "tensorflow-ocaml: OCaml bindings for TensorFlow". GitHub. Archived from the original on June 11, 2018. Retrieved February 18, 2018. <a href="https://github.com/LaurentMazare/tensorflow-ocaml" target="_blank">https://github.com/LaurentMazare/tensorflow-ocaml</a> <a href="#fnref:68" class="footnote-back-ref">↩</a></p></li> <li id="fn:69"><p>"fazibear/tensorflow.cr". GitHub. Archived from the original on June 27, 2018. Retrieved October 10, 2018. <a href="https://github.com/fazibear/tensorflow.cr" target="_blank">https://github.com/fazibear/tensorflow.cr</a> <a href="#fnref:69" class="footnote-back-ref">↩</a></p></li> <li id="fn:70"><p>"tensorflow package - github.com/tensorflow/tensorflow/tensorflow/go - pkg.go.dev". pkg.go.dev. Archived from the original on November 6, 2021. Retrieved November 6, 2021. <a href="https://pkg.go.dev/github.com/tensorflow/tensorflow/tensorflow/go" target="_blank">https://pkg.go.dev/github.com/tensorflow/tensorflow/tensorflow/go</a> <a href="#fnref:70" class="footnote-back-ref">↩</a></p></li> <li id="fn:71"><p>"Swift for TensorFlow (In Archive Mode)". TensorFlow. Archived from the original on November 6, 2021. Retrieved November 6, 2021. <a href="https://www.tensorflow.org/swift/guide/overview" target="_blank">https://www.tensorflow.org/swift/guide/overview</a> <a href="#fnref:71" class="footnote-back-ref">↩</a></p></li> <li id="fn:72"><p>"Introduction to TensorFlow". TensorFlow. Archived from the original on January 20, 2023. Retrieved October 28, 2021. <a href="https://www.tensorflow.org/learn" target="_blank">https://www.tensorflow.org/learn</a> <a href="#fnref:72" class="footnote-back-ref">↩</a></p></li> <li id="fn:73"><p>"TensorFlow.js | Machine Learning for JavaScript Developers". TensorFlow. Archived from the original on November 4, 2021. Retrieved October 28, 2021. <a href="https://www.tensorflow.org/js" target="_blank">https://www.tensorflow.org/js</a> <a href="#fnref:73" class="footnote-back-ref">↩</a></p></li> <li id="fn:74"><p>"TensorFlow Lite | ML for Mobile and Edge Devices". TensorFlow. Archived from the original on November 4, 2021. Retrieved November 1, 2021. <a href="https://www.tensorflow.org/lite" target="_blank">https://www.tensorflow.org/lite</a> <a href="#fnref:74" class="footnote-back-ref">↩</a></p></li> <li id="fn:75"><p>"TensorFlow Lite". TensorFlow. Archived from the original on November 2, 2021. Retrieved November 1, 2021. <a href="https://www.tensorflow.org/lite/guide" target="_blank">https://www.tensorflow.org/lite/guide</a> <a href="#fnref:75" class="footnote-back-ref">↩</a></p></li> <li id="fn:76"><p>"TensorFlow Lite". TensorFlow. Archived from the original on November 2, 2021. Retrieved November 1, 2021. <a href="https://www.tensorflow.org/lite/guide" target="_blank">https://www.tensorflow.org/lite/guide</a> <a href="#fnref:76" class="footnote-back-ref">↩</a></p></li> <li id="fn:77"><p>"TensorFlow Extended (TFX) | ML Production Pipelines". TensorFlow. Archived from the original on November 4, 2021. Retrieved November 2, 2021. <a href="https://www.tensorflow.org/tfx" target="_blank">https://www.tensorflow.org/tfx</a> <a href="#fnref:77" class="footnote-back-ref">↩</a></p></li> <li id="fn:78"><p>"Introduction to TensorFlow". TensorFlow. Archived from the original on January 20, 2023. Retrieved October 28, 2021. <a href="https://www.tensorflow.org/learn" target="_blank">https://www.tensorflow.org/learn</a> <a href="#fnref:78" class="footnote-back-ref">↩</a></p></li> <li id="fn:79"><p>"TensorFlow Extended (TFX) | ML Production Pipelines". TensorFlow. Archived from the original on November 4, 2021. Retrieved November 2, 2021. <a href="https://www.tensorflow.org/tfx" target="_blank">https://www.tensorflow.org/tfx</a> <a href="#fnref:79" class="footnote-back-ref">↩</a></p></li> <li id="fn:80"><p>"Customization basics: tensors and operations | TensorFlow Core". TensorFlow. Archived from the original on November 6, 2021. Retrieved November 6, 2021. <a href="https://www.tensorflow.org/tutorials/customization/basics" target="_blank">https://www.tensorflow.org/tutorials/customization/basics</a> <a href="#fnref:80" class="footnote-back-ref">↩</a></p></li> <li id="fn:81"><p>"Customization basics: tensors and operations | TensorFlow Core". TensorFlow. Archived from the original on November 6, 2021. Retrieved November 6, 2021. <a href="https://www.tensorflow.org/tutorials/customization/basics" target="_blank">https://www.tensorflow.org/tutorials/customization/basics</a> <a href="#fnref:81" class="footnote-back-ref">↩</a></p></li> <li id="fn:82"><p>"Customization basics: tensors and operations | TensorFlow Core". TensorFlow. Archived from the original on November 6, 2021. Retrieved November 6, 2021. <a href="https://www.tensorflow.org/tutorials/customization/basics" target="_blank">https://www.tensorflow.org/tutorials/customization/basics</a> <a href="#fnref:82" class="footnote-back-ref">↩</a></p></li> <li id="fn:83"><p>"Guide | TensorFlow Core". TensorFlow. Archived from the original on July 17, 2019. Retrieved November 4, 2021. <a href="https://www.tensorflow.org/guide" target="_blank">https://www.tensorflow.org/guide</a> <a href="#fnref:83" class="footnote-back-ref">↩</a></p></li> <li id="fn:84"><p>"Libraries & extensions". TensorFlow. Archived from the original on November 4, 2021. Retrieved November 4, 2021. <a href="https://www.tensorflow.org/resources/libraries-extensions" target="_blank">https://www.tensorflow.org/resources/libraries-extensions</a> <a href="#fnref:84" class="footnote-back-ref">↩</a></p></li> <li id="fn:85"><p>"Guide | TensorFlow Core". TensorFlow. Archived from the original on July 17, 2019. Retrieved November 4, 2021. <a href="https://www.tensorflow.org/guide" target="_blank">https://www.tensorflow.org/guide</a> <a href="#fnref:85" class="footnote-back-ref">↩</a></p></li> <li id="fn:86"><p>"Libraries & extensions". TensorFlow. Archived from the original on November 4, 2021. Retrieved November 4, 2021. <a href="https://www.tensorflow.org/resources/libraries-extensions" target="_blank">https://www.tensorflow.org/resources/libraries-extensions</a> <a href="#fnref:86" class="footnote-back-ref">↩</a></p></li> <li id="fn:87"><p>"Colaboratory – Google". research.google.com. Archived from the original on October 24, 2017. Retrieved November 10, 2018. <a href="https://research.google.com/colaboratory/faq.html" target="_blank">https://research.google.com/colaboratory/faq.html</a> <a href="#fnref:87" class="footnote-back-ref">↩</a></p></li> <li id="fn:88"><p>"Google Colaboratory". colab.research.google.com. Archived from the original on February 3, 2021. Retrieved November 6, 2021. <a href="https://colab.research.google.com/" target="_blank">https://colab.research.google.com/</a> <a href="#fnref:88" class="footnote-back-ref">↩</a></p></li> <li id="fn:89"><p>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), "JAX: Autograd and XLA", Astrophysics Source Code Library, Google, Bibcode:2021ascl.soft11002B, archived from the original on June 18, 2022, retrieved June 18, 2022 <a href="https://web.archive.org/web/20220618205214/https://github.com/google/jax" target="_blank">https://web.archive.org/web/20220618205214/https://github.com/google/jax</a> <a href="#fnref:89" class="footnote-back-ref">↩</a></p></li> <li id="fn:90"><p>"Using JAX to accelerate our research". www.deepmind.com. Archived from the original on June 18, 2022. Retrieved June 18, 2022. <a href="https://www.deepmind.com/blog/using-jax-to-accelerate-our-research" target="_blank">https://www.deepmind.com/blog/using-jax-to-accelerate-our-research</a> <a href="#fnref:90" class="footnote-back-ref">↩</a></p></li> <li id="fn:91"><p>"Why is Google's JAX so popular?". Analytics India Magazine. April 25, 2022. Archived from the original on June 18, 2022. Retrieved June 18, 2022. <a href="https://analyticsindiamag.com/why-is-googles-jax-so-popular/" target="_blank">https://analyticsindiamag.com/why-is-googles-jax-so-popular/</a> <a href="#fnref:91" class="footnote-back-ref">↩</a></p></li> <li id="fn:92"><p>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), "JAX: Autograd and XLA", Astrophysics Source Code Library, Google, Bibcode:2021ascl.soft11002B, archived from the original on June 18, 2022, retrieved June 18, 2022 <a href="https://web.archive.org/web/20220618205214/https://github.com/google/jax" target="_blank">https://web.archive.org/web/20220618205214/https://github.com/google/jax</a> <a href="#fnref:92" class="footnote-back-ref">↩</a></p></li> <li id="fn:93"><p>"Intelligent Scanning Using Deep Learning for MRI". Archived from the original on November 4, 2021. Retrieved November 4, 2021. <a href="https://blog.tensorflow.org/2019/03/intelligent-scanning-using-deep-learning.html" target="_blank">https://blog.tensorflow.org/2019/03/intelligent-scanning-using-deep-learning.html</a> <a href="#fnref:93" class="footnote-back-ref">↩</a></p></li> <li id="fn:94"><p>"Case Studies and Mentions". TensorFlow. Archived from the original on October 26, 2021. Retrieved November 4, 2021. <a href="https://www.tensorflow.org/about/case-studies" target="_blank">https://www.tensorflow.org/about/case-studies</a> <a href="#fnref:94" class="footnote-back-ref">↩</a></p></li> <li id="fn:95"><p>"Case Studies and Mentions". TensorFlow. Archived from the original on October 26, 2021. Retrieved November 4, 2021. <a href="https://www.tensorflow.org/about/case-studies" target="_blank">https://www.tensorflow.org/about/case-studies</a> <a href="#fnref:95" class="footnote-back-ref">↩</a></p></li> <li id="fn:96"><p>"Ranking Tweets with TensorFlow". Archived from the original on November 4, 2021. Retrieved November 4, 2021. <a href="https://blog.tensorflow.org/2019/03/ranking-tweets-with-tensorflow.html" target="_blank">https://blog.tensorflow.org/2019/03/ranking-tweets-with-tensorflow.html</a> <a href="#fnref:96" class="footnote-back-ref">↩</a></p></li> <li id="fn:97"><p>"Ranking Tweets with TensorFlow". Archived from the original on November 4, 2021. Retrieved November 4, 2021. <a href="https://blog.tensorflow.org/2019/03/ranking-tweets-with-tensorflow.html" target="_blank">https://blog.tensorflow.org/2019/03/ranking-tweets-with-tensorflow.html</a> <a href="#fnref:97" class="footnote-back-ref">↩</a></p></li> <li id="fn:98"><p>"Case Studies and Mentions". TensorFlow. Archived from the original on October 26, 2021. Retrieved November 4, 2021. <a href="https://www.tensorflow.org/about/case-studies" target="_blank">https://www.tensorflow.org/about/case-studies</a> <a href="#fnref:98" class="footnote-back-ref">↩</a></p></li> <li id="fn:99"><p>Davies, Dave (September 2, 2020). "A Complete Guide to the Google RankBrain Algorithm". Search Engine Journal. Archived from the original on November 6, 2021. Retrieved October 15, 2024. <a href="https://www.searchenginejournal.com/google-algorithm-history/rankbrain/" target="_blank">https://www.searchenginejournal.com/google-algorithm-history/rankbrain/</a> <a href="#fnref:99" class="footnote-back-ref">↩</a></p></li> <li id="fn:100"><p>"InSpace: A new video conferencing platform that uses TensorFlow.js for toxicity filters in chat". Archived from the original on November 4, 2021. Retrieved November 4, 2021. <a href="https://blog.tensorflow.org/2020/12/inspace-new-video-conferencing-platform-uses-tensorflowjs-for-toxicity-filters-in-chat.html" target="_blank">https://blog.tensorflow.org/2020/12/inspace-new-video-conferencing-platform-uses-tensorflowjs-for-toxicity-filters-in-chat.html</a> <a href="#fnref:100" class="footnote-back-ref">↩</a></p></li> <li id="fn:101"><p>Xulin. "流利说基于 TensorFlow 的自适应系统实践". Weixin Official Accounts Platform. Archived from the original on November 6, 2021. Retrieved November 4, 2021. <a href="http://mp.weixin.qq.com/s?__biz=MzI0NjIzNDkwOA==&mid=2247484035&idx=1&sn=85fa0decac95e359435f68c50865ac0b&chksm=e94328f0de34a1e665e0d809b938efb34f0aa6034391891246fc223b7782ac3bfd6ddd588aa2#rd" target="_blank">http://mp.weixin.qq.com/s?__biz=MzI0NjIzNDkwOA==&mid=2247484035&idx=1&sn=85fa0decac95e359435f68c50865ac0b&chksm=e94328f0de34a1e665e0d809b938efb34f0aa6034391891246fc223b7782ac3bfd6ddd588aa2#rd</a> <a href="#fnref:101" class="footnote-back-ref">↩</a></p></li> <li id="fn:102"><p>Xulin. "流利说基于 TensorFlow 的自适应系统实践". Weixin Official Accounts Platform. Archived from the original on November 6, 2021. Retrieved November 4, 2021. <a href="http://mp.weixin.qq.com/s?__biz=MzI0NjIzNDkwOA==&mid=2247484035&idx=1&sn=85fa0decac95e359435f68c50865ac0b&chksm=e94328f0de34a1e665e0d809b938efb34f0aa6034391891246fc223b7782ac3bfd6ddd588aa2#rd" target="_blank">http://mp.weixin.qq.com/s?__biz=MzI0NjIzNDkwOA==&mid=2247484035&idx=1&sn=85fa0decac95e359435f68c50865ac0b&chksm=e94328f0de34a1e665e0d809b938efb34f0aa6034391891246fc223b7782ac3bfd6ddd588aa2#rd</a> <a href="#fnref:102" class="footnote-back-ref">↩</a></p></li> <li id="fn:103"><p>"Case Studies and Mentions". TensorFlow. Archived from the original on October 26, 2021. Retrieved November 4, 2021. <a href="https://www.tensorflow.org/about/case-studies" target="_blank">https://www.tensorflow.org/about/case-studies</a> <a href="#fnref:103" class="footnote-back-ref">↩</a></p></li> <li id="fn:104"><p>"How Modiface utilized TensorFlow.js in production for AR makeup try on in the browser". Archived from the original on November 4, 2021. Retrieved November 4, 2021. <a href="https://blog.tensorflow.org/2020/02/how-modiface-utilized-tensorflowjs-in-ar-makeup-in-browser.html" target="_blank">https://blog.tensorflow.org/2020/02/how-modiface-utilized-tensorflowjs-in-ar-makeup-in-browser.html</a> <a href="#fnref:104" class="footnote-back-ref">↩</a></p></li> <li id="fn:105"><p>Byrne, Michael (November 11, 2015). "Google Offers Up Its Entire Machine Learning Library as Open-Source Software". Vice. Archived from the original on January 25, 2021. Retrieved November 11, 2015. <a href="https://www.vice.com/en/article/8q8avx/google-offers-up-its-entire-machine-learning-library-as-open-source" target="_blank">https://www.vice.com/en/article/8q8avx/google-offers-up-its-entire-machine-learning-library-as-open-source</a> <a href="#fnref:105" class="footnote-back-ref">↩</a></p></li> </ol>