2018:
1975:
1966:
6291:
5377:
5156:
40:
6271:
5166:
1484:, 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which changed the automatic differentiation scheme from the static computational graph to the "Define-by-Run" scheme originally made popular by
2305:
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;
1467:
In May 2017, Google announced a software stack specifically for mobile development, TensorFlow Lite. 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. In
1522:
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. Code executed eagerly can be examined step-by step-through a debugger, since data is augmented at each line of code rather
1943:
InSpace, a virtual learning platform, used TensorFlow to filter out toxic chat messages in classrooms. Liulishuo, an online
English learning platform, utilized TensorFlow to create an adaptive curriculum for each student. TensorFlow was used to accurately assess a student's current abilities, and
1764:
TensorFlow
Extended (abbrev. TFX) provides numerous components to perform all the operations needed for end-to-end production. Components include loading, validating, and transforming data, tuning, training, and evaluating the machine learning model, and pushing the model itself into production.
1782:
data libraries, and TensorFlow offers integration and compatibility with its data structures. Numpy NDarrays, the library's native datatype, are automatically converted to TensorFlow
Tensors in TF operations; the same is also true vice versa. This allows for the two libraries to work in unison
4626:
1803:
for their respective functionalities in recommendation systems and graphics, TensorFlow
Federated provides a framework for decentralized data, and TensorFlow Cloud allows users to directly interact with Google Cloud to integrate their local code to Google Cloud. Other add-ons,
1508:
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
4618:
1744:
TensorFlow Lite has APIs for mobile apps or embedded devices to generate and deploy TensorFlow models. These models are compressed and optimized in order to be more efficient and have a higher performance on smaller capacity devices.
1567:
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
1915:
implemented TensorFlow to rank tweets by importance for a given user, and changed their platform to show tweets in order of this ranking. Previously, tweets were simply shown in reverse chronological order. The photo sharing app
1513:
which require gradients to optimize performance. 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.
1956:
used TensorFlow to provide personalized recommendations for customers. The cosmetics company ModiFace used TensorFlow to create an augmented reality experience for customers to test various shades of make-up on their face.
1783:
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.
1820:
Google also released
Colaboratory, a TensorFlow Jupyter notebook environment that does not require any setup. It runs on Google Cloud and allows users free access to GPUs and the ability to store and share notebooks on
2585:
2554:
1649:
to allow users to make their own machine-learning models. 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.
4592:
4352:
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),
1896:
in identifying specific body parts. Google used TensorFlow to create DermAssist, a free mobile application that allows users to take pictures of their skin and identify potential health complications.
2616:
1492:. 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.
6686:
6165:
2826:
2950:
1036:
3098:
2860:
1074:
4683:
3007:
3038:
1278:
3778:
operations like sin, * (matrix multiplication), .* (element-wise multiplication), etc . Compare to Python, which requires learning specialized namespaced functions like tf.matmul.
2688:
4652:
2764:
1031:
2657:
1021:
6007:
862:
5413:
5202:
4574:
2577:
2546:
2419:
4588:
2362:"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
1069:
1736:
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.
4455:
2890:
1531:
In both eager and graph executions, TensorFlow provides an API for distributing computation across multiple devices with various distribution strategies. This
6681:
2981:
1026:
877:
6666:
2118:
608:
6691:
6661:
1109:
912:
2453:
2795:
2608:
4552:
4521:
3640:
3124:
2192:
2155:
1632:(SGD). When training a model, different optimizers offer different modes of parameter tuning, often affecting a model's convergence and performance.
4957:
2326:
2818:
5523:
3068:
2942:
1452:
1375:
1371:
988:
537:
4399:
3094:
2852:
2081:
5406:
4010:
1325:. The name TensorFlow derives from the operations that such neural networks perform on multidimensional data arrays, which are referred to as
6337:
4675:
3441:
3258:
3003:
6196:
5222:
5211:
5195:
3030:
2031:
2023:
1523:
than later in a computational graph. This execution paradigm is considered to be easier to debug because of its step by step transparency.
1046:
809:
344:
4429:
6297:
5848:
5585:
4980:
4744:
2680:
1141:
1064:
4267:
4201:
3550:
6671:
6624:
5126:
4648:
3398:
3225:
1379:
897:
872:
821:
2756:
2520:
6109:
5736:
5543:
5399:
2639:
2221:
2186:
2149:
2112:
2075:
1233:
the codebase of DistBelief into a faster, more robust application-grade library, which became TensorFlow. In 2009, the team, led by
945:
940:
593:
3335:
1398:
them. Google announced they had been running TPUs inside their data centers for more than a year, and had found them to deliver an
3305:
6064:
3832:
1455:
chip designed to run TensorFlow Lite machine learning (ML) models on small client computing devices such as smartphones known as
603:
241:
6656:
6630:
5188:
4297:
3950:
3673:
3368:
1535:
can often speed up the execution of training and evaluating of TensorFlow models and is a common practice in the field of AI.
998:
6414:
6251:
6191:
5789:
4040:
3891:
2505:
1713:
1681:
1677:
1226:
1102:
762:
583:
4492:
6399:
5784:
5473:
3455:
1779:
1654:
1621:
1179:
1126:
973:
675:
451:
104:
3272:
2738:
6226:
5580:
5533:
5528:
5310:
3706:
2882:
2409:
1901:
1721:
1701:
1685:
1589:
930:
867:
777:
755:
598:
588:
81:
3980:
3157:
6578:
6404:
6277:
5573:
5499:
5275:
5058:
3765:
1705:
1673:
1629:
1601:
1191:
1081:
993:
978:
439:
261:
3800:
2714:
1468:
May 2019, Google announced that their TensorFlow Lite Micro (also known as TensorFlow Lite for
Microcontrollers) and
968:
4451:
3610:
3192:
1812:
include TensorFlow Model Optimization, TensorFlow Probability, TensorFlow Quantum, and TensorFlow Decision Forests.
1799:
to advance and extend the models and methods used. For example, TensorFlow Recommenders and TensorFlow Graphics are
6588:
5901:
5836:
5437:
4133:
3858:
3732:
2036:
1893:
1304:
Its flexible architecture allows for the easy deployment of computation across a variety of platforms (CPUs, GPUs,
1294:
1257:
TensorFlow is Google Brain's second-generation system. Version 1.0.0 was released on February 11, 2017. While the
1041:
718:
613:
401:
334:
294:
136:
2973:
2482:
6409:
6330:
6302:
6160:
5799:
5630:
5453:
5115:
3485:
1717:
1585:
1548:
1505:
1218:
1095:
701:
469:
339:
4327:
3917:
2098:
1378:, a hardware chip) built specifically for machine learning and tailored for TensorFlow. A TPU is a programmable
1225:
companies in both research and commercial applications. Google assigned multiple computer scientists, including
6676:
6432:
6201:
5458:
5305:
5159:
4851:
1316:
1258:
723:
643:
566:
484:
314:
276:
271:
231:
226:
4234:
3520:
4100:
2445:
6437:
6373:
6246:
6231:
5884:
5879:
5779:
5647:
5428:
5070:
4737:
4717:
4166:
4070:
2787:
2283:
1262:
1137:
670:
519:
419:
246:
4354:
3580:
3422:"A Comparative Analysis of Gradient Descent-Based Optimization Algorithms on Convolutional Neural Networks"
2920:
6696:
6562:
6368:
6206:
5966:
5685:
5680:
5380:
4990:
4845:
4544:
4517:
3632:
3120:
2257:
2172:
2135:
1367:
1361:
1305:
850:
826:
728:
489:
464:
424:
236:
2307:
6635:
6236:
6221:
6186:
5874:
5774:
5642:
5046:
4857:
1532:
1440:
1429:
1410:
1145:
804:
626:
578:
434:
349:
221:
6104:
3060:
2315:. Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI ’16).
1850:(automatic obtaining of the gradient function through differentiation of a function) and TensorFlow's
39:
6537:
6462:
6383:
6323:
6256:
6211:
5657:
5602:
5448:
5443:
5330:
5232:
5169:
4911:
4391:
4362:
3426:
2018 International Conference on Computational Techniques, Electronics and Mechanical Systems (CTEMS)
2213:
2061:
1569:
1403:
1319:
1208:
1149:
733:
683:
4002:
1974:
5831:
5809:
5558:
5553:
5511:
5463:
5356:
5121:
1953:
1897:
1805:
1800:
1796:
1792:
1593:
1395:
1129:
836:
772:
743:
648:
474:
407:
393:
379:
354:
304:
256:
216:
155:
147:
6270:
6477:
6216:
5794:
5623:
4730:
4589:"InSpace: A new video conferencing platform that uses TensorFlow.js for toxicity filters in chat"
3447:
2547:"Google Open-Sources The Machine Learning Tech Behind Google Photos Search, Smart Reply And More"
2357:
2316:
1846:
for transforming numerical functions. It is described as bringing together a modified version of
1843:
1809:
1552:
1399:
1246:
1172:
814:
738:
524:
319:
167:
119:
1409:
In May 2017, Google announced the second-generation, as well as the availability of the TPUs in
1349:
In Jan 2019, Google announced TensorFlow 2.0. It became officially available in September 2019.
4421:
6547:
6487:
6282:
6074:
5726:
5597:
5590:
5346:
5300:
4810:
4568:
3437:
3264:
3254:
2217:
2182:
2178:
2145:
2141:
2108:
2104:
2071:
2067:
907:
750:
663:
459:
429:
374:
369:
324:
266:
1645:
TensorFlow serves as a core platform and library for machine learning. TensorFlow's APIs use
6552:
6482:
6452:
6027:
6017:
5824:
5618:
5568:
5563:
5506:
5494:
5250:
5141:
5029:
5017:
4259:
4193:
3542:
3429:
2649:
1999:
1753:
1605:
1597:
1230:
1211:
1133:
935:
688:
638:
548:
532:
502:
364:
359:
309:
299:
197:
162:
152:
3390:
3217:
6140:
6084:
5906:
5548:
5468:
5351:
4963:
4774:
2742:
2509:
2414:
1510:
1352:
In May 2019, Google announced TensorFlow Graphics for deep learning in computer graphics.
1238:
1234:
963:
767:
633:
573:
4366:
3420:
Dogo, E. M.; Afolabi, O. J.; Nwulu, N. I.; Twala, B.; Aigbavboa, C. O. (December 2018).
3327:
6618:
6315:
6114:
6079:
6069:
5894:
5652:
5478:
5255:
4875:
4649:"How Modiface utilized TensorFlow.js in production for AR makeup try on in the browser"
3297:
1456:
1439:
In February 2018, Google announced that they were making TPUs available in beta on the
1322:
1242:
1171:'s internal use in research and production. The initial version was released under the
983:
514:
251:
3822:
6650:
6059:
6039:
5956:
5635:
5023:
4923:
3451:
2848:
1889:
1858:
as closely as possible and works with TensorFlow as well as other frameworks such as
1854:(Accelerated Linear Algebra). It is designed to follow the structure and workflow of
1732:
TensorFlow also has a library for machine learning in JavaScript. Using the provided
1693:
1573:
1556:
1544:
1480:
As TensorFlow's market share among research papers was declining to the advantage of
1222:
1215:
1153:
902:
831:
713:
444:
329:
4289:
3940:
1965:
6512:
6492:
6145:
5976:
5245:
5240:
5136:
4816:
4769:
3663:
3360:
1822:
1697:
1469:
1164:
55:
4032:
4003:"tensorflow package - github.com/tensorflow/tensorflow/tensorflow/go - pkg.go.dev"
3881:
1342:
In March 2018, Google announced TensorFlow.js version 1.0 for machine learning in
6472:
6447:
6241:
6012:
5921:
5916:
5538:
5516:
5131:
5093:
4484:
3250:
Distributed Computing and Artificial Intelligence, 11th International Conference
1944:
also helped decide the best future content to show based on those capabilities.
1749:
1609:
1417:
of performance, and when organized into clusters of 64 TPUs, provide up to 11.5
1309:
1175:
in 2015. Google released an updated version, TensorFlow 2.0, in September 2019.
708:
202:
3433:
3421:
3004:"Google's new machine learning framework is going to put more AI on your phone"
2681:"TensorFlow, Google's Open Source AI, Points to a Fast-Changing Hardware World"
6583:
6522:
6378:
6135:
6094:
6089:
6002:
5911:
5819:
5731:
5338:
4883:
4676:"Google Offers Up Its Entire Machine Learning Library as Open-Source Software"
2735:
2351:
2013:
1839:
1834:
1733:
1665:
1620:
TensorFlow offers a set of optimizers for training neural networks, including
1387:
1383:
1343:
1332:
1245:
with substantially higher accuracy, for instance a 25% reduction in errors in
1183:
857:
553:
479:
140:
50:
3696:
3268:
1451:
In July 2018, the Edge TPU was announced. Edge TPU is Google's purpose-built
1424:
In May 2018, Google announced the third-generation TPUs delivering up to 420
1178:
TensorFlow can be used in a wide variety of programming languages, including
6442:
6130:
6099:
5997:
5841:
5804:
5741:
5695:
5690:
5675:
5320:
5260:
5076:
4905:
4822:
4753:
3972:
3149:
2003:
1932:
1016:
797:
5391:
3755:
2653:
87:
17:
3790:
2710:
2609:"Google chairman: We're making 'real progress' on artificial intelligence"
6598:
6542:
6032:
5864:
5315:
5180:
4917:
3602:
3184:
2410:"Google Just Open Sourced TensorFlow, Its Artificial Intelligence Engine"
4125:
3854:
3728:
2819:"Introducing TensorFlow Graphics: Computer Graphics Meets Deep Learning"
6527:
6507:
6467:
6457:
6155:
5992:
5946:
5869:
5769:
5764:
5716:
5341:
5290:
4951:
4804:
2478:
1912:
1859:
1625:
1489:
1485:
1481:
1290:
1157:
1140:. It can be used across a range of tasks but has a particular focus on
792:
132:
3477:
2883:"Build and train machine learning models on our new Google Cloud TPUs"
38:
6593:
6532:
6517:
6346:
6170:
6150:
6022:
5814:
5361:
5285:
5280:
4828:
4764:
4319:
3945:
3913:
3886:
3882:"tensorflow_scala: TensorFlow API for the Scala Programming Language"
3827:
3795:
3760:
3701:
3668:
3248:
2644:
2383:
2371:
1928:
1689:
1588:
operations on models. Some of these operations include variations of
1336:
1327:
1168:
543:
4226:
3512:
2510:"TensorFlow: Large-scale machine learning on heterogeneous systems"
2321:
1847:
1752:
as the data serialization format for network models, eschewing the
1669:
1194:, facilitating its use in a range of applications in many sectors.
1187:
108:
5971:
5951:
5941:
5936:
5931:
5926:
5889:
5721:
5270:
5052:
4092:
2100:
Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow
2041:
1855:
1709:
1646:
1433:
1425:
1418:
1414:
1391:
1286:
1282:
787:
782:
509:
128:
124:
4158:
3031:"TensorFlow Lite Now Faster with Mobile GPUs (Developer Preview)"
2853:"Google supercharges machine learning tasks with TPU custom chip"
2279:
2171:
Hope, Tom; Resheff, Yehezkel S.; Lieder, Itay (August 27, 2017).
1851:
1664:), as well as APIs without backwards compatibility guarantee for
6502:
6497:
5961:
5265:
5064:
4370:
4194:"Customization basics: tensors and operations | TensorFlow Core"
4062:
2912:
1917:
1274:
1270:
112:
6319:
5395:
5184:
4726:
2943:"Cloud TPU machine learning accelerators now available in beta"
2249:
1676:. Third-party language binding packages are also available for
3478:"TensorFlow Core | Machine Learning for Beginners and Experts"
2974:"Google Announces Edge TPU, Cloud IoT Edge at Cloud Next 2018"
2174:
Learning TensorFlow: A Guide to Building Deep Learning Systems
1661:
1657:
1298:
1266:
4710:
3572:
1983:
2016 comparison of original photo (left) and with TensorFlow
4722:
4063:"TensorFlow.js | Machine Learning for JavaScript Developers"
2578:"What Is TensorFlow, and Why Is Google So Excited About It?"
2757:"Introducing TensorFlow.js: Machine Learning in Javascript"
1920:
used TensorFlow to help suggest custom filters for photos.
1900:
used TensorFlow to identify and classify eye diseases from
1394:), and oriented toward using or running models rather than
1335:
in June 2016, Jeff Dean stated that 1,500 repositories on
1308:), and from desktops to clusters of servers to mobile and
3150:"Introduction to gradients and automatic differentiation"
2134:
Ramsundar, Bharath; Zadeh, Reza Bosagh (March 23, 2018).
1716:. Bindings that are now archived and unsupported include
1543:
To train and assess models, TensorFlow provides a set of
178:
3823:"Use TensorFlow from Pascal (FreePascal, Lazarus, etc.)"
1339:
mentioned TensorFlow, of which only 5 were from Google.
1075:
List of datasets in computer vision and image processing
3697:"TensorFlow.NET: .NET Standard bindings for TensorFlow"
3603:"TensorFlow C++ API Reference | TensorFlow Core v2.7.0"
1261:
runs on single devices, TensorFlow can run on multiple
3543:"All symbols in TensorFlow 2 | TensorFlow Core v2.7.0"
1892:
used TensorFlow to increase the speed and accuracy of
1279:
general-purpose computing on graphics processing units
4159:"TensorFlow Extended (TFX) | ML Production Pipelines"
2736:
Machine Learning: Google I/O 2016 Minute 07:30/44:44
2309:
TensorFlow: A System for Large-Scale Machine Learning
1207:
Starting in 2011, Google Brain built DistBelief as a
4545:"A Complete Guide to the Google RankBrain Algorithm"
3664:"TensorFlowSharp: TensorFlow API for .NET languages"
1608:, etc.) and their variations, and other operations (
1241:
and other improvements, which allowed generation of
6611:
6571:
6423:
6392:
6361:
6354:
6179:
6123:
6052:
5985:
5857:
5757:
5750:
5704:
5668:
5611:
5487:
5427:
5329:
5231:
5107:
5086:
5039:
5010:
5003:
4973:
4944:
4937:
4898:
4867:
4838:
4797:
4790:
4783:
173:
161:
146:
118:
100:
80:
62:
49:
6687:Python (programming language) scientific libraries
4452:"Intelligent Scanning Using Deep Learning for MRI"
4093:"TensorFlow Lite | ML for Mobile and Edge Devices"
3095:"The State of Machine Learning Frameworks in 2019"
2306:Wicke, Martin; Yu, Yuan; Zheng, Xiaoqiang (2016).
1584:TensorFlow.nn is a module for executing primitive
3941:"tensorflow-ocaml: OCaml bindings for TensorFlow"
3391:"Module: tf.optimizers | TensorFlow Core v2.7.0"
3218:"Module: tf.distribute | TensorFlow Core v2.6.1"
2508:; Monga, Rajat; et al. (November 9, 2015).
1998:TensorFlow is the foundation for the automated
1413:. The second-generation TPUs deliver up to 180
1070:List of datasets for machine-learning research
6331:
5407:
5196:
4738:
3914:"rust: Rust language bindings for TensorFlow"
3328:"Module: tf.metrics | TensorFlow Core v2.6.1"
3061:"uTensor and Tensor Flow Announcement | Mbed"
1103:
8:
3298:"Module: tf.losses | TensorFlow Core v2.6.1"
32:
4573:: CS1 maint: numeric names: authors list (
1935:on October 26, 2015, backed by TensorFlow.
1756:format used by standard TensorFlow models.
1432:memory (HBM). Cloud TPU v3 Pods offer 100+
1293:, and mobile computing platforms including
6358:
6338:
6324:
6316:
5754:
5414:
5400:
5392:
5203:
5189:
5181:
5007:
4941:
4794:
4787:
4745:
4731:
4723:
4543:3.5kshares; 72kreads (September 2, 2020).
3729:"haskell: Haskell bindings for TensorFlow"
2395:
2384:Video clip by Google about TensorFlow 2015
2372:Video clip by Google about TensorFlow 2015
1110:
1096:
188:
31:
2320:
2244:
2242:
1315:TensorFlow computations are expressed as
4033:"Swift for TensorFlow (In Archive Mode)"
3880:Platanios, Anthony (February 17, 2018).
3361:"Module: tf.nn | TensorFlow Core v2.7.0"
2353:TensorFlow: Open source machine learning
4347:
4345:
3803:from the original on September 14, 2020
3123:. TensorFlow Blog. September 30, 2019.
2619:from the original on September 16, 2015
2607:Ward-Bailey, Jeff (November 25, 2015).
2360:from the original on November 11, 2021.
2238:
1372:application-specific integrated circuit
196:
4566:
4392:"Using JAX to accelerate our research"
4254:
4252:
4221:
4219:
4188:
4186:
4184:
4120:
4118:
3894:from the original on February 18, 2019
3791:"A MATLAB wrapper for TensorFlow Core"
3662:Icaza, Miguel de (February 17, 2018).
3355:
3353:
2953:from the original on February 12, 2018
2691:from the original on November 11, 2015
2660:from the original on February 27, 2021
2588:from the original on November 10, 2015
2526:from the original on November 20, 2015
2485:from the original on November 16, 2015
2473:
2471:
2332:from the original on December 12, 2020
2260:from the original on November 17, 2015
1221:. Its use grew rapidly across diverse
4686:from the original on January 25, 2021
4655:from the original on November 4, 2021
4629:from the original on November 6, 2021
4612:
4610:
4595:from the original on November 4, 2021
4555:from the original on November 6, 2021
4524:from the original on November 4, 2021
4512:
4510:
4495:from the original on October 26, 2021
4479:
4477:
4475:
4473:
4458:from the original on November 4, 2021
4330:from the original on February 3, 2021
4300:from the original on October 24, 2017
4270:from the original on November 4, 2021
4204:from the original on November 6, 2021
4169:from the original on November 4, 2021
4153:
4151:
4136:from the original on November 2, 2021
4103:from the original on November 4, 2021
4073:from the original on November 4, 2021
4043:from the original on November 6, 2021
4013:from the original on November 6, 2021
3939:Mazare, Laurent (February 16, 2018).
3835:from the original on January 20, 2023
3643:from the original on November 6, 2021
3613:from the original on January 20, 2023
3553:from the original on November 6, 2021
3523:from the original on January 20, 2023
3507:
3505:
3503:
3488:from the original on January 20, 2023
3401:from the original on October 30, 2021
3338:from the original on November 4, 2021
3308:from the original on October 27, 2021
3292:
3290:
3253:. Springer International Publishing.
3212:
3210:
3195:from the original on November 4, 2021
3179:
3177:
3175:
3160:from the original on October 28, 2021
3144:
3142:
3127:from the original on October 30, 2019
3101:from the original on October 10, 2019
3088:
3086:
3041:from the original on January 16, 2019
2798:from the original on January 14, 2019
2557:from the original on November 9, 2015
2439:
2437:
2422:from the original on November 9, 2015
2208:Shukla, Nishant (February 12, 2018).
2060:Moroney, Laurence (October 1, 2020).
1281:). TensorFlow is available on 64-bit
7:
6252:Generative adversarial network (GAN)
5165:
4674:Byrne, Michael (November 11, 2015).
3861:from the original on January 4, 2017
2456:from the original on October 7, 2019
2097:Géron, Aurélien (October 15, 2019).
2032:Comparison of deep learning software
2024:Free and open-source software portal
1862:. The primary functions of JAX are:
1791:TensorFlow also offers a variety of
1152:. It is one of the two most popular
6682:Open-source artificial intelligence
4981:Quantum Artificial Intelligence Lab
3695:Chen, Haiping (December 11, 2018).
3185:"Eager execution | TensorFlow Core"
2767:from the original on March 30, 2018
1065:Glossary of artificial intelligence
6667:Free software programmed in Python
6625:Google LLC v. Oracle America, Inc.
5127:Generative pre-trained transformer
4432:from the original on June 18, 2022
4402:from the original on June 18, 2022
4237:from the original on July 17, 2019
3983:from the original on June 27, 2018
3953:from the original on June 11, 2018
3920:from the original on July 24, 2017
3768:from the original on July 24, 2017
3735:from the original on July 24, 2017
3709:from the original on July 12, 2019
3676:from the original on July 24, 2017
3121:"TensorFlow 2.0 is now available!"
2972:Kundu, Kishalaya (July 26, 2018).
2446:"TensorFlow 2.0 is now available!"
2195:from the original on March 8, 2021
2063:AI and Machine Learning for Coders
1366:In May 2016, Google announced its
25:
6692:Software using the Apache license
4718:Learning TensorFlow.js Book (ENG)
4623:Weixin Official Accounts Platform
4422:"Why is Google's JAX so popular?"
3916:. tensorflow. February 17, 2018.
3731:. tensorflow. February 17, 2018.
3583:from the original on May 26, 2024
3458:from the original on May 26, 2024
3371:from the original on May 26, 2024
3275:from the original on May 26, 2024
3228:from the original on May 26, 2024
3010:from the original on May 17, 2017
2984:from the original on May 26, 2024
2923:from the original on May 17, 2017
2893:from the original on May 17, 2017
2863:from the original on May 18, 2016
2788:"What's coming in TensorFlow 2.0"
2717:from the original on May 26, 2024
2576:Oremus, Will (November 9, 2015).
2545:Perez, Sarah (November 9, 2015).
2444:TensorFlow (September 30, 2019).
2158:from the original on June 7, 2021
2084:from the original on June 7, 2021
1778:Numpy is one of the most popular
1551:). Some popular examples include
27:Machine learning software library
6290:
6289:
6269:
5376:
5375:
5164:
5155:
5154:
4518:"Ranking Tweets with TensorFlow"
4359:Astrophysics Source Code Library
3756:"A Julia wrapper for TensorFlow"
3754:Malmaud, Jon (August 12, 2019).
3071:from the original on May 9, 2019
2829:from the original on May 9, 2019
2679:Metz, Cade (November 10, 2015).
2286:from the original on May 6, 2018
2210:Machine Learning with TensorFlow
2121:from the original on May 1, 2021
2016:
1973:
1964:
6662:Free software programmed in C++
6631:Open Source Security Foundation
3093:He, Horace (October 10, 2019).
3029:TensorFlow (January 16, 2019).
2786:TensorFlow (January 14, 2019).
2408:Metz, Cade (November 9, 2015).
1866:grad: automatic differentiation
1428:of performance and 128 GB high
6202:Recurrent neural network (RNN)
6192:Differentiable neural computer
3857:. RStudio. February 17, 2018.
3855:"tensorflow: TensorFlow for R"
2638:TensorFlow Developers (2022).
1436:of performance and 32 TB HBM.
1237:, had implemented generalized
485:Relevance vector machine (RVM)
1:
6349:free and open-source software
6247:Variational autoencoder (VAE)
6207:Long short-term memory (LSTM)
5474:Computational learning theory
2755:TensorFlow (March 30, 2018).
1658:Application Program Interface
1653:TensorFlow provides a stable
1592:(1/2/3D, Atrous, depthwise),
974:Computational learning theory
538:Expectation–maximization (EM)
6227:Convolutional neural network
4260:"Libraries & extensions"
3513:"Introduction to TensorFlow"
2137:TensorFlow for Deep Learning
1902:optical coherence tomography
1356:Tensor processing unit (TPU)
931:Coefficient of determination
778:Convolutional neural network
490:Support vector machine (SVM)
6222:Multilayer perceptron (MLP)
5276:Microsoft Cognitive Toolkit
4619:"流利说基于 TensorFlow 的自适应系统实践"
4485:"Case Studies and Mentions"
1630:Stochastic Gradient Descent
1082:Outline of machine learning
979:Empirical risk minimization
6713:
6298:Artificial neural networks
6212:Gated recurrent unit (GRU)
5438:Differentiable programming
3434:10.1109/CTEMS.2018.8769211
2947:Google Cloud Platform Blog
2857:Google Cloud Platform Blog
2817:TensorFlow (May 9, 2019).
2741:December 21, 2016, at the
2640:"Tensorflow Release 1.0.0"
2037:Differentiable programming
1832:
1472:uTensor would be merging.
1359:
719:Feedforward neural network
470:Artificial neural networks
6672:Free statistical software
6265:
5631:Artificial neural network
5454:Automatic differentiation
5371:
5218:
5150:
5116:Attention Is All You Need
4760:
4324:colab.research.google.com
4227:"Guide | TensorFlow Core"
2711:"Introduction to tensors"
1382:designed to provide high
702:Artificial neural network
37:
5459:Neuromorphic engineering
5422:Differentiable computing
4426:Analytics India Magazine
3973:"fazibear/tensorflow.cr"
1952:The e-commerce platform
1872:vmap: auto-vectorization
1259:reference implementation
1163:It was developed by the
1011:Journals and conferences
958:Mathematical foundations
868:Temporal difference (TD)
724:Recurrent neural network
644:Conditional random field
567:Dimensionality reduction
315:Dimensionality reduction
277:Quantum machine learning
272:Neuromorphic engineering
232:Self-supervised learning
227:Semi-supervised learning
6232:Residual neural network
5648:Artificial Intelligence
4355:"JAX: Autograd and XLA"
4290:"Colaboratory – Google"
3633:"org.tensorflow | Java"
3247:Sigeru., Omatu (2014).
1574:Intersection-over-Union
1138:artificial intelligence
420:Apprenticeship learning
6657:Deep learning software
5212:Deep learning software
4991:Tensor Processing Unit
2654:10.5281/zenodo.4724125
1875:pmap: SPMD programming
1842:is a machine learning
1406:for machine learning.
1368:Tensor processing unit
1362:Tensor processing unit
969:Bias–variance tradeoff
851:Reinforcement learning
827:Spiking neural network
237:Reinforcement learning
44:
6393:Programming languages
6187:Neural Turing machine
5775:Human image synthesis
5364:Deep Learning Toolbox
4549:Search Engine Journal
4320:"Google Colaboratory"
2745:accessdate=2016-06-05
1748:TensorFlow Lite uses
1533:distributed computing
1441:Google Cloud Platform
1411:Google Compute Engine
1333:Google I/O Conference
805:Neural radiance field
627:Structured prediction
350:Structured prediction
222:Unsupervised learning
68:; 8 years ago
66:November 9, 2015
42:
6278:Computer programming
6257:Graph neural network
5832:Text-to-video models
5810:Text-to-image models
5658:Large language model
5643:Scientific computing
5449:Statistical manifold
5444:Information geometry
3831:. January 19, 2023.
3799:. November 3, 2019.
2214:Manning Publications
1931:officially released
1636:Usage and extensions
1594:activation functions
1557:binary cross entropy
1404:performance per watt
1156:libraries alongside
1150:deep neural networks
1127:free and open-source
994:Statistical learning
892:Learning with humans
684:Local outlier factor
5624:In-context learning
5464:Pattern recognition
5357:Wolfram Mathematica
5122:Future of Go Summit
4367:2021ascl.soft11002B
4294:research.google.com
2519:. Google Research.
2479:"API Documentation"
2386:at minute 0:26/2:17
2374:at minute 0:15/2:17
1898:Sinovation Ventures
1612:, bias-add, etc.).
1506:AutoDifferentiation
1501:AutoDifferentiation
837:Electrochemical RAM
744:reservoir computing
475:Logistic regression
394:Supervised learning
380:Multimodal learning
355:Feature engineering
300:Generative modeling
262:Rule-based learning
257:Curriculum learning
217:Supervised learning
192:Part of a series on
34:
6217:Echo state network
6105:Jürgen Schmidhuber
5800:Facial recognition
5795:Speech recognition
5705:Software libraries
4868:In popular culture
4428:. April 25, 2022.
3428:. pp. 92–99.
2713:. tensorflow.org.
1553:mean squared error
1400:order of magnitude
1247:speech recognition
1229:, to simplify and
1173:Apache License 2.0
405: •
320:Density estimation
168:Apache License 2.0
45:
6644:
6643:
6607:
6606:
6572:Operating systems
6426:development tools
6313:
6312:
6075:Stephen Grossberg
6048:
6047:
5389:
5388:
5178:
5177:
5103:
5102:
4999:
4998:
4933:
4932:
4894:
4893:
4784:Computer programs
4126:"TensorFlow Lite"
3577:js.tensorflow.org
3443:978-1-5386-7709-4
3260:978-3-319-07593-8
1570:Precision, Recall
1402:better-optimized
1386:of low-precision
1120:
1119:
925:Model diagnostics
908:Human-in-the-loop
751:Boltzmann machine
664:Anomaly detection
460:Linear regression
375:Ontology learning
370:Grammar induction
345:Semantic analysis
340:Association rules
325:Anomaly detection
267:Neuro-symbolic AI
187:
186:
16:(Redirected from
6704:
6553:Protocol Buffers
6359:
6340:
6333:
6326:
6317:
6303:Machine learning
6293:
6292:
6273:
6028:Action selection
6018:Self-driving car
5825:Stable Diffusion
5790:Speech synthesis
5755:
5619:Machine learning
5495:Gradient descent
5416:
5409:
5402:
5393:
5379:
5378:
5205:
5198:
5191:
5182:
5168:
5167:
5158:
5157:
5142:Google Workspace
5008:
4942:
4938:Machine learning
4795:
4788:
4747:
4740:
4733:
4724:
4714:
4713:
4711:Official website
4696:
4695:
4693:
4691:
4671:
4665:
4664:
4662:
4660:
4645:
4639:
4638:
4636:
4634:
4614:
4605:
4604:
4602:
4600:
4585:
4579:
4578:
4572:
4564:
4562:
4560:
4540:
4534:
4533:
4531:
4529:
4514:
4505:
4504:
4502:
4500:
4481:
4468:
4467:
4465:
4463:
4448:
4442:
4441:
4439:
4437:
4418:
4412:
4411:
4409:
4407:
4396:www.deepmind.com
4388:
4382:
4381:
4380:
4378:
4373:on June 18, 2022
4369:, archived from
4349:
4340:
4339:
4337:
4335:
4316:
4310:
4309:
4307:
4305:
4286:
4280:
4279:
4277:
4275:
4256:
4247:
4246:
4244:
4242:
4223:
4214:
4213:
4211:
4209:
4190:
4179:
4178:
4176:
4174:
4155:
4146:
4145:
4143:
4141:
4122:
4113:
4112:
4110:
4108:
4089:
4083:
4082:
4080:
4078:
4059:
4053:
4052:
4050:
4048:
4029:
4023:
4022:
4020:
4018:
3999:
3993:
3992:
3990:
3988:
3969:
3963:
3962:
3960:
3958:
3936:
3930:
3929:
3927:
3925:
3910:
3904:
3903:
3901:
3899:
3877:
3871:
3870:
3868:
3866:
3851:
3845:
3844:
3842:
3840:
3819:
3813:
3812:
3810:
3808:
3787:
3781:
3780:
3775:
3773:
3751:
3745:
3744:
3742:
3740:
3725:
3719:
3718:
3716:
3714:
3692:
3686:
3685:
3683:
3681:
3659:
3653:
3652:
3650:
3648:
3629:
3623:
3622:
3620:
3618:
3599:
3593:
3592:
3590:
3588:
3569:
3563:
3562:
3560:
3558:
3539:
3533:
3532:
3530:
3528:
3509:
3498:
3497:
3495:
3493:
3474:
3468:
3467:
3465:
3463:
3417:
3411:
3410:
3408:
3406:
3387:
3381:
3380:
3378:
3376:
3357:
3348:
3347:
3345:
3343:
3324:
3318:
3317:
3315:
3313:
3294:
3285:
3284:
3282:
3280:
3244:
3238:
3237:
3235:
3233:
3214:
3205:
3204:
3202:
3200:
3181:
3170:
3169:
3167:
3165:
3146:
3137:
3136:
3134:
3132:
3117:
3111:
3110:
3108:
3106:
3097:. The Gradient.
3090:
3081:
3080:
3078:
3076:
3057:
3051:
3050:
3048:
3046:
3026:
3020:
3019:
3017:
3015:
3006:. May 17, 2017.
3000:
2994:
2993:
2991:
2989:
2969:
2963:
2962:
2960:
2958:
2939:
2933:
2932:
2930:
2928:
2909:
2903:
2902:
2900:
2898:
2889:. May 17, 2017.
2879:
2873:
2872:
2870:
2868:
2845:
2839:
2838:
2836:
2834:
2814:
2808:
2807:
2805:
2803:
2783:
2777:
2776:
2774:
2772:
2752:
2746:
2733:
2727:
2726:
2724:
2722:
2707:
2701:
2700:
2698:
2696:
2676:
2670:
2669:
2667:
2665:
2635:
2629:
2628:
2626:
2624:
2604:
2598:
2597:
2595:
2593:
2573:
2567:
2566:
2564:
2562:
2542:
2536:
2535:
2533:
2531:
2525:
2514:
2502:
2496:
2494:
2492:
2490:
2475:
2466:
2465:
2463:
2461:
2441:
2432:
2431:
2429:
2427:
2405:
2399:
2393:
2387:
2381:
2375:
2369:
2363:
2361:
2356:. Google. 2015.
2348:
2342:
2341:
2339:
2337:
2331:
2324:
2314:
2302:
2296:
2295:
2293:
2291:
2276:
2270:
2269:
2267:
2265:
2246:
2227:
2212:(1st ed.).
2204:
2202:
2200:
2177:(1st ed.).
2167:
2165:
2163:
2140:(1st ed.).
2130:
2128:
2126:
2103:(2nd ed.).
2093:
2091:
2089:
2066:(1st ed.).
2026:
2021:
2020:
2019:
2000:image-captioning
1977:
1968:
1869:jit: compilation
1754:Protocol Buffers
1214:system based on
1212:machine learning
1134:machine learning
1130:software library
1112:
1105:
1098:
1059:Related articles
936:Confusion matrix
689:Isolation forest
634:Graphical models
413:
412:
365:Learning to rank
360:Feature learning
198:Machine learning
189:
183:
180:
153:Machine learning
96:
93:
91:
89:
76:
74:
69:
35:
21:
6712:
6711:
6707:
6706:
6705:
6703:
6702:
6701:
6677:Google software
6647:
6646:
6645:
6640:
6603:
6567:
6425:
6419:
6388:
6350:
6344:
6314:
6309:
6261:
6175:
6141:Google DeepMind
6119:
6085:Geoffrey Hinton
6044:
5981:
5907:Project Debater
5853:
5751:Implementations
5746:
5700:
5664:
5607:
5549:Backpropagation
5483:
5469:Tensor calculus
5423:
5420:
5390:
5385:
5367:
5352:Neural Designer
5325:
5227:
5214:
5209:
5179:
5174:
5146:
5099:
5082:
5040:Language models
5035:
4995:
4969:
4945:Neural networks
4929:
4890:
4863:
4834:
4779:
4775:Google DeepMind
4756:
4751:
4709:
4708:
4705:
4700:
4699:
4689:
4687:
4673:
4672:
4668:
4658:
4656:
4647:
4646:
4642:
4632:
4630:
4616:
4615:
4608:
4598:
4596:
4587:
4586:
4582:
4565:
4558:
4556:
4542:
4541:
4537:
4527:
4525:
4516:
4515:
4508:
4498:
4496:
4483:
4482:
4471:
4461:
4459:
4450:
4449:
4445:
4435:
4433:
4420:
4419:
4415:
4405:
4403:
4390:
4389:
4385:
4376:
4374:
4351:
4350:
4343:
4333:
4331:
4318:
4317:
4313:
4303:
4301:
4288:
4287:
4283:
4273:
4271:
4258:
4257:
4250:
4240:
4238:
4225:
4224:
4217:
4207:
4205:
4192:
4191:
4182:
4172:
4170:
4157:
4156:
4149:
4139:
4137:
4124:
4123:
4116:
4106:
4104:
4091:
4090:
4086:
4076:
4074:
4061:
4060:
4056:
4046:
4044:
4031:
4030:
4026:
4016:
4014:
4001:
4000:
3996:
3986:
3984:
3971:
3970:
3966:
3956:
3954:
3938:
3937:
3933:
3923:
3921:
3912:
3911:
3907:
3897:
3895:
3879:
3878:
3874:
3864:
3862:
3853:
3852:
3848:
3838:
3836:
3821:
3820:
3816:
3806:
3804:
3789:
3788:
3784:
3771:
3769:
3753:
3752:
3748:
3738:
3736:
3727:
3726:
3722:
3712:
3710:
3694:
3693:
3689:
3679:
3677:
3661:
3660:
3656:
3646:
3644:
3631:
3630:
3626:
3616:
3614:
3601:
3600:
3596:
3586:
3584:
3573:"TensorFlow.js"
3571:
3570:
3566:
3556:
3554:
3541:
3540:
3536:
3526:
3524:
3511:
3510:
3501:
3491:
3489:
3476:
3475:
3471:
3461:
3459:
3444:
3419:
3418:
3414:
3404:
3402:
3389:
3388:
3384:
3374:
3372:
3359:
3358:
3351:
3341:
3339:
3326:
3325:
3321:
3311:
3309:
3296:
3295:
3288:
3278:
3276:
3261:
3246:
3245:
3241:
3231:
3229:
3216:
3215:
3208:
3198:
3196:
3183:
3182:
3173:
3163:
3161:
3148:
3147:
3140:
3130:
3128:
3119:
3118:
3114:
3104:
3102:
3092:
3091:
3084:
3074:
3072:
3059:
3058:
3054:
3044:
3042:
3028:
3027:
3023:
3013:
3011:
3002:
3001:
2997:
2987:
2985:
2971:
2970:
2966:
2956:
2954:
2941:
2940:
2936:
2926:
2924:
2911:
2910:
2906:
2896:
2894:
2881:
2880:
2876:
2866:
2864:
2847:
2846:
2842:
2832:
2830:
2816:
2815:
2811:
2801:
2799:
2785:
2784:
2780:
2770:
2768:
2754:
2753:
2749:
2743:Wayback Machine
2734:
2730:
2720:
2718:
2709:
2708:
2704:
2694:
2692:
2678:
2677:
2673:
2663:
2661:
2637:
2636:
2632:
2622:
2620:
2606:
2605:
2601:
2591:
2589:
2575:
2574:
2570:
2560:
2558:
2544:
2543:
2539:
2529:
2527:
2523:
2512:
2504:
2503:
2499:
2488:
2486:
2477:
2476:
2469:
2459:
2457:
2443:
2442:
2435:
2425:
2423:
2407:
2406:
2402:
2396:Dean et al 2015
2394:
2390:
2382:
2378:
2370:
2366:
2350:
2349:
2345:
2335:
2333:
2329:
2312:
2304:
2303:
2299:
2289:
2287:
2280:"TensorFlow.js"
2278:
2277:
2273:
2263:
2261:
2248:
2247:
2240:
2235:
2230:
2224:
2216:. p. 272.
2207:
2198:
2196:
2189:
2181:. p. 242.
2170:
2161:
2159:
2152:
2144:. p. 256.
2133:
2124:
2122:
2115:
2107:. p. 856.
2096:
2087:
2085:
2078:
2070:. p. 365.
2059:
2055:
2050:
2022:
2017:
2015:
2012:
1996:
1991:
1990:
1989:
1988:
1987:applied (right)
1980:
1979:
1978:
1970:
1969:
1950:
1941:
1926:
1910:
1887:
1882:
1837:
1831:
1818:
1789:
1776:
1771:
1762:
1742:
1730:
1643:
1638:
1618:
1582:
1565:
1547:(also known as
1541:
1529:
1520:
1518:Eager execution
1511:backpropagation
1503:
1498:
1478:
1465:
1463:TensorFlow Lite
1449:
1364:
1358:
1277:extensions for
1269:(with optional
1255:
1243:neural networks
1239:backpropagation
1235:Geoffrey Hinton
1219:neural networks
1205:
1200:
1116:
1087:
1086:
1060:
1052:
1051:
1012:
1004:
1003:
964:Kernel machines
959:
951:
950:
926:
918:
917:
898:Active learning
893:
885:
884:
853:
843:
842:
768:Diffusion model
704:
694:
693:
666:
656:
655:
629:
619:
618:
574:Factor analysis
569:
559:
558:
542:
505:
495:
494:
415:
414:
398:
397:
396:
385:
384:
290:
282:
281:
247:Online learning
212:
200:
177:
86:
72:
70:
67:
63:Initial release
43:TensorFlow logo
28:
23:
22:
15:
12:
11:
5:
6710:
6708:
6700:
6699:
6694:
6689:
6684:
6679:
6674:
6669:
6664:
6659:
6649:
6648:
6642:
6641:
6639:
6638:
6636:Summer of Code
6633:
6628:
6621:
6615:
6613:
6609:
6608:
6605:
6604:
6602:
6601:
6596:
6591:
6586:
6581:
6575:
6573:
6569:
6568:
6566:
6565:
6560:
6555:
6550:
6545:
6540:
6535:
6530:
6525:
6520:
6515:
6510:
6505:
6500:
6495:
6490:
6485:
6480:
6475:
6470:
6465:
6460:
6455:
6450:
6445:
6440:
6435:
6429:
6427:
6424:Frameworks and
6421:
6420:
6418:
6417:
6412:
6407:
6402:
6396:
6394:
6390:
6389:
6387:
6386:
6381:
6376:
6371:
6365:
6363:
6356:
6352:
6351:
6345:
6343:
6342:
6335:
6328:
6320:
6311:
6310:
6308:
6307:
6306:
6305:
6300:
6287:
6286:
6285:
6280:
6266:
6263:
6262:
6260:
6259:
6254:
6249:
6244:
6239:
6234:
6229:
6224:
6219:
6214:
6209:
6204:
6199:
6194:
6189:
6183:
6181:
6177:
6176:
6174:
6173:
6168:
6163:
6158:
6153:
6148:
6143:
6138:
6133:
6127:
6125:
6121:
6120:
6118:
6117:
6115:Ilya Sutskever
6112:
6107:
6102:
6097:
6092:
6087:
6082:
6080:Demis Hassabis
6077:
6072:
6070:Ian Goodfellow
6067:
6062:
6056:
6054:
6050:
6049:
6046:
6045:
6043:
6042:
6037:
6036:
6035:
6025:
6020:
6015:
6010:
6005:
6000:
5995:
5989:
5987:
5983:
5982:
5980:
5979:
5974:
5969:
5964:
5959:
5954:
5949:
5944:
5939:
5934:
5929:
5924:
5919:
5914:
5909:
5904:
5899:
5898:
5897:
5887:
5882:
5877:
5872:
5867:
5861:
5859:
5855:
5854:
5852:
5851:
5846:
5845:
5844:
5839:
5829:
5828:
5827:
5822:
5817:
5807:
5802:
5797:
5792:
5787:
5782:
5777:
5772:
5767:
5761:
5759:
5752:
5748:
5747:
5745:
5744:
5739:
5734:
5729:
5724:
5719:
5714:
5708:
5706:
5702:
5701:
5699:
5698:
5693:
5688:
5683:
5678:
5672:
5670:
5666:
5665:
5663:
5662:
5661:
5660:
5653:Language model
5650:
5645:
5640:
5639:
5638:
5628:
5627:
5626:
5615:
5613:
5609:
5608:
5606:
5605:
5603:Autoregression
5600:
5595:
5594:
5593:
5583:
5581:Regularization
5578:
5577:
5576:
5571:
5566:
5556:
5551:
5546:
5544:Loss functions
5541:
5536:
5531:
5526:
5521:
5520:
5519:
5509:
5504:
5503:
5502:
5491:
5489:
5485:
5484:
5482:
5481:
5479:Inductive bias
5476:
5471:
5466:
5461:
5456:
5451:
5446:
5441:
5433:
5431:
5425:
5424:
5421:
5419:
5418:
5411:
5404:
5396:
5387:
5386:
5384:
5383:
5372:
5369:
5368:
5366:
5365:
5359:
5354:
5349:
5344:
5335:
5333:
5327:
5326:
5324:
5323:
5318:
5313:
5308:
5303:
5298:
5293:
5288:
5283:
5278:
5273:
5268:
5263:
5258:
5256:Deeplearning4j
5253:
5248:
5243:
5237:
5235:
5229:
5228:
5226:
5225:
5219:
5216:
5215:
5210:
5208:
5207:
5200:
5193:
5185:
5176:
5175:
5173:
5172:
5162:
5151:
5148:
5147:
5145:
5144:
5139:
5134:
5129:
5124:
5119:
5111:
5109:
5105:
5104:
5101:
5100:
5098:
5097:
5090:
5088:
5084:
5083:
5081:
5080:
5074:
5068:
5062:
5056:
5050:
5043:
5041:
5037:
5036:
5034:
5033:
5027:
5021:
5014:
5012:
5005:
5001:
5000:
4997:
4996:
4994:
4993:
4988:
4983:
4977:
4975:
4971:
4970:
4968:
4967:
4961:
4955:
4948:
4946:
4939:
4935:
4934:
4931:
4930:
4928:
4927:
4921:
4915:
4909:
4902:
4900:
4896:
4895:
4892:
4891:
4889:
4888:
4880:
4871:
4869:
4865:
4864:
4862:
4861:
4855:
4849:
4842:
4840:
4836:
4835:
4833:
4832:
4826:
4820:
4814:
4808:
4801:
4799:
4792:
4785:
4781:
4780:
4778:
4777:
4772:
4767:
4761:
4758:
4757:
4752:
4750:
4749:
4742:
4735:
4727:
4721:
4720:
4715:
4704:
4703:External links
4701:
4698:
4697:
4666:
4640:
4606:
4580:
4535:
4506:
4469:
4443:
4413:
4383:
4341:
4311:
4281:
4248:
4215:
4180:
4147:
4114:
4084:
4054:
4024:
3994:
3964:
3931:
3905:
3872:
3846:
3814:
3782:
3746:
3720:
3687:
3654:
3624:
3594:
3564:
3534:
3499:
3469:
3442:
3412:
3382:
3349:
3319:
3286:
3259:
3239:
3206:
3171:
3138:
3112:
3082:
3052:
3021:
2995:
2964:
2934:
2904:
2874:
2840:
2809:
2778:
2747:
2728:
2702:
2671:
2630:
2599:
2568:
2537:
2517:TensorFlow.org
2497:
2467:
2433:
2400:
2388:
2376:
2364:
2343:
2297:
2271:
2254:TensorFlow.org
2237:
2236:
2234:
2231:
2229:
2228:
2222:
2205:
2187:
2179:O'Reilly Media
2168:
2150:
2142:O'Reilly Media
2131:
2113:
2105:O'Reilly Media
2094:
2076:
2068:O'Reilly Media
2056:
2054:
2051:
2049:
2046:
2045:
2044:
2039:
2034:
2028:
2027:
2011:
2008:
1995:
1992:
1982:
1981:
1972:
1971:
1963:
1962:
1961:
1960:
1959:
1949:
1946:
1940:
1937:
1925:
1922:
1909:
1906:
1886:
1883:
1881:
1878:
1877:
1876:
1873:
1870:
1867:
1833:Main article:
1830:
1827:
1817:
1814:
1788:
1785:
1775:
1772:
1770:
1767:
1761:
1758:
1741:
1738:
1729:
1726:
1642:
1639:
1637:
1634:
1617:
1614:
1586:neural network
1581:
1578:
1564:
1561:
1549:cost functions
1545:loss functions
1540:
1537:
1528:
1525:
1519:
1516:
1502:
1499:
1497:
1494:
1477:
1476:TensorFlow 2.0
1474:
1464:
1461:
1457:edge computing
1448:
1445:
1380:AI accelerator
1360:Main article:
1357:
1354:
1254:
1251:
1204:
1201:
1199:
1196:
1118:
1117:
1115:
1114:
1107:
1100:
1092:
1089:
1088:
1085:
1084:
1079:
1078:
1077:
1067:
1061:
1058:
1057:
1054:
1053:
1050:
1049:
1044:
1039:
1034:
1029:
1024:
1019:
1013:
1010:
1009:
1006:
1005:
1002:
1001:
996:
991:
986:
984:Occam learning
981:
976:
971:
966:
960:
957:
956:
953:
952:
949:
948:
943:
941:Learning curve
938:
933:
927:
924:
923:
920:
919:
916:
915:
910:
905:
900:
894:
891:
890:
887:
886:
883:
882:
881:
880:
870:
865:
860:
854:
849:
848:
845:
844:
841:
840:
834:
829:
824:
819:
818:
817:
807:
802:
801:
800:
795:
790:
785:
775:
770:
765:
760:
759:
758:
748:
747:
746:
741:
736:
731:
721:
716:
711:
705:
700:
699:
696:
695:
692:
691:
686:
681:
673:
667:
662:
661:
658:
657:
654:
653:
652:
651:
646:
641:
630:
625:
624:
621:
620:
617:
616:
611:
606:
601:
596:
591:
586:
581:
576:
570:
565:
564:
561:
560:
557:
556:
551:
546:
540:
535:
530:
522:
517:
512:
506:
501:
500:
497:
496:
493:
492:
487:
482:
477:
472:
467:
462:
457:
449:
448:
447:
442:
437:
427:
425:Decision trees
422:
416:
402:classification
392:
391:
390:
387:
386:
383:
382:
377:
372:
367:
362:
357:
352:
347:
342:
337:
332:
327:
322:
317:
312:
307:
302:
297:
295:Classification
291:
288:
287:
284:
283:
280:
279:
274:
269:
264:
259:
254:
252:Batch learning
249:
244:
239:
234:
229:
224:
219:
213:
210:
209:
206:
205:
194:
193:
185:
184:
175:
171:
170:
165:
159:
158:
150:
144:
143:
122:
116:
115:
102:
98:
97:
84:
78:
77:
64:
60:
59:
53:
47:
46:
26:
24:
14:
13:
10:
9:
6:
4:
3:
2:
6709:
6698:
6697:2015 software
6695:
6693:
6690:
6688:
6685:
6683:
6680:
6678:
6675:
6673:
6670:
6668:
6665:
6663:
6660:
6658:
6655:
6654:
6652:
6637:
6634:
6632:
6629:
6627:
6626:
6622:
6620:
6617:
6616:
6614:
6610:
6600:
6597:
6595:
6592:
6590:
6587:
6585:
6582:
6580:
6577:
6576:
6574:
6570:
6564:
6561:
6559:
6556:
6554:
6551:
6549:
6546:
6544:
6541:
6539:
6536:
6534:
6531:
6529:
6526:
6524:
6521:
6519:
6516:
6514:
6511:
6509:
6506:
6504:
6501:
6499:
6496:
6494:
6491:
6489:
6486:
6484:
6481:
6479:
6476:
6474:
6471:
6469:
6466:
6464:
6463:Closure Tools
6461:
6459:
6456:
6454:
6451:
6449:
6446:
6444:
6441:
6439:
6436:
6434:
6431:
6430:
6428:
6422:
6416:
6413:
6411:
6408:
6406:
6403:
6401:
6398:
6397:
6395:
6391:
6385:
6382:
6380:
6377:
6375:
6372:
6370:
6367:
6366:
6364:
6360:
6357:
6353:
6348:
6341:
6336:
6334:
6329:
6327:
6322:
6321:
6318:
6304:
6301:
6299:
6296:
6295:
6288:
6284:
6281:
6279:
6276:
6275:
6272:
6268:
6267:
6264:
6258:
6255:
6253:
6250:
6248:
6245:
6243:
6240:
6238:
6235:
6233:
6230:
6228:
6225:
6223:
6220:
6218:
6215:
6213:
6210:
6208:
6205:
6203:
6200:
6198:
6195:
6193:
6190:
6188:
6185:
6184:
6182:
6180:Architectures
6178:
6172:
6169:
6167:
6164:
6162:
6159:
6157:
6154:
6152:
6149:
6147:
6144:
6142:
6139:
6137:
6134:
6132:
6129:
6128:
6126:
6124:Organizations
6122:
6116:
6113:
6111:
6108:
6106:
6103:
6101:
6098:
6096:
6093:
6091:
6088:
6086:
6083:
6081:
6078:
6076:
6073:
6071:
6068:
6066:
6063:
6061:
6060:Yoshua Bengio
6058:
6057:
6055:
6051:
6041:
6040:Robot control
6038:
6034:
6031:
6030:
6029:
6026:
6024:
6021:
6019:
6016:
6014:
6011:
6009:
6006:
6004:
6001:
5999:
5996:
5994:
5991:
5990:
5988:
5984:
5978:
5975:
5973:
5970:
5968:
5965:
5963:
5960:
5958:
5957:Chinchilla AI
5955:
5953:
5950:
5948:
5945:
5943:
5940:
5938:
5935:
5933:
5930:
5928:
5925:
5923:
5920:
5918:
5915:
5913:
5910:
5908:
5905:
5903:
5900:
5896:
5893:
5892:
5891:
5888:
5886:
5883:
5881:
5878:
5876:
5873:
5871:
5868:
5866:
5863:
5862:
5860:
5856:
5850:
5847:
5843:
5840:
5838:
5835:
5834:
5833:
5830:
5826:
5823:
5821:
5818:
5816:
5813:
5812:
5811:
5808:
5806:
5803:
5801:
5798:
5796:
5793:
5791:
5788:
5786:
5783:
5781:
5778:
5776:
5773:
5771:
5768:
5766:
5763:
5762:
5760:
5756:
5753:
5749:
5743:
5740:
5738:
5735:
5733:
5730:
5728:
5725:
5723:
5720:
5718:
5715:
5713:
5710:
5709:
5707:
5703:
5697:
5694:
5692:
5689:
5687:
5684:
5682:
5679:
5677:
5674:
5673:
5671:
5667:
5659:
5656:
5655:
5654:
5651:
5649:
5646:
5644:
5641:
5637:
5636:Deep learning
5634:
5633:
5632:
5629:
5625:
5622:
5621:
5620:
5617:
5616:
5614:
5610:
5604:
5601:
5599:
5596:
5592:
5589:
5588:
5587:
5584:
5582:
5579:
5575:
5572:
5570:
5567:
5565:
5562:
5561:
5560:
5557:
5555:
5552:
5550:
5547:
5545:
5542:
5540:
5537:
5535:
5532:
5530:
5527:
5525:
5524:Hallucination
5522:
5518:
5515:
5514:
5513:
5510:
5508:
5505:
5501:
5498:
5497:
5496:
5493:
5492:
5490:
5486:
5480:
5477:
5475:
5472:
5470:
5467:
5465:
5462:
5460:
5457:
5455:
5452:
5450:
5447:
5445:
5442:
5440:
5439:
5435:
5434:
5432:
5430:
5426:
5417:
5412:
5410:
5405:
5403:
5398:
5397:
5394:
5382:
5374:
5373:
5370:
5363:
5360:
5358:
5355:
5353:
5350:
5348:
5345:
5343:
5340:
5337:
5336:
5334:
5332:
5328:
5322:
5319:
5317:
5314:
5312:
5309:
5307:
5304:
5302:
5299:
5297:
5294:
5292:
5289:
5287:
5284:
5282:
5279:
5277:
5274:
5272:
5269:
5267:
5264:
5262:
5259:
5257:
5254:
5252:
5249:
5247:
5244:
5242:
5239:
5238:
5236:
5234:
5230:
5224:
5221:
5220:
5217:
5213:
5206:
5201:
5199:
5194:
5192:
5187:
5186:
5183:
5171:
5163:
5161:
5153:
5152:
5149:
5143:
5140:
5138:
5135:
5133:
5130:
5128:
5125:
5123:
5120:
5117:
5113:
5112:
5110:
5106:
5095:
5092:
5091:
5089:
5085:
5078:
5075:
5072:
5069:
5066:
5063:
5060:
5057:
5054:
5051:
5048:
5045:
5044:
5042:
5038:
5031:
5028:
5025:
5022:
5019:
5016:
5015:
5013:
5009:
5006:
5004:Generative AI
5002:
4992:
4989:
4987:
4984:
4982:
4979:
4978:
4976:
4972:
4965:
4962:
4959:
4956:
4953:
4950:
4949:
4947:
4943:
4940:
4936:
4925:
4924:AlphaGeometry
4922:
4919:
4916:
4913:
4910:
4907:
4904:
4903:
4901:
4897:
4886:
4885:
4881:
4878:
4877:
4873:
4872:
4870:
4866:
4859:
4856:
4853:
4850:
4847:
4844:
4843:
4841:
4837:
4830:
4827:
4824:
4821:
4818:
4815:
4812:
4809:
4806:
4803:
4802:
4800:
4796:
4793:
4789:
4786:
4782:
4776:
4773:
4771:
4768:
4766:
4763:
4762:
4759:
4755:
4748:
4743:
4741:
4736:
4734:
4729:
4728:
4725:
4719:
4716:
4712:
4707:
4706:
4702:
4685:
4681:
4677:
4670:
4667:
4654:
4650:
4644:
4641:
4628:
4624:
4620:
4613:
4611:
4607:
4594:
4590:
4584:
4581:
4576:
4570:
4554:
4550:
4546:
4539:
4536:
4523:
4519:
4513:
4511:
4507:
4494:
4490:
4486:
4480:
4478:
4476:
4474:
4470:
4457:
4453:
4447:
4444:
4431:
4427:
4423:
4417:
4414:
4401:
4397:
4393:
4387:
4384:
4372:
4368:
4364:
4360:
4356:
4348:
4346:
4342:
4329:
4325:
4321:
4315:
4312:
4299:
4295:
4291:
4285:
4282:
4269:
4265:
4261:
4255:
4253:
4249:
4236:
4232:
4228:
4222:
4220:
4216:
4203:
4199:
4195:
4189:
4187:
4185:
4181:
4168:
4164:
4160:
4154:
4152:
4148:
4135:
4131:
4127:
4121:
4119:
4115:
4102:
4098:
4094:
4088:
4085:
4072:
4068:
4064:
4058:
4055:
4042:
4038:
4034:
4028:
4025:
4012:
4008:
4004:
3998:
3995:
3982:
3978:
3974:
3968:
3965:
3952:
3948:
3947:
3942:
3935:
3932:
3919:
3915:
3909:
3906:
3893:
3889:
3888:
3883:
3876:
3873:
3860:
3856:
3850:
3847:
3834:
3830:
3829:
3824:
3818:
3815:
3802:
3798:
3797:
3792:
3786:
3783:
3779:
3767:
3763:
3762:
3757:
3750:
3747:
3734:
3730:
3724:
3721:
3708:
3704:
3703:
3698:
3691:
3688:
3675:
3671:
3670:
3665:
3658:
3655:
3642:
3638:
3634:
3628:
3625:
3612:
3608:
3604:
3598:
3595:
3582:
3578:
3574:
3568:
3565:
3552:
3548:
3544:
3538:
3535:
3522:
3518:
3514:
3508:
3506:
3504:
3500:
3487:
3483:
3479:
3473:
3470:
3457:
3453:
3449:
3445:
3439:
3435:
3431:
3427:
3423:
3416:
3413:
3400:
3396:
3392:
3386:
3383:
3370:
3366:
3362:
3356:
3354:
3350:
3337:
3333:
3329:
3323:
3320:
3307:
3303:
3299:
3293:
3291:
3287:
3274:
3270:
3266:
3262:
3256:
3252:
3251:
3243:
3240:
3227:
3223:
3219:
3213:
3211:
3207:
3194:
3190:
3186:
3180:
3178:
3176:
3172:
3159:
3155:
3151:
3145:
3143:
3139:
3126:
3122:
3116:
3113:
3100:
3096:
3089:
3087:
3083:
3070:
3066:
3062:
3056:
3053:
3040:
3036:
3032:
3025:
3022:
3009:
3005:
2999:
2996:
2983:
2979:
2975:
2968:
2965:
2952:
2948:
2944:
2938:
2935:
2922:
2918:
2914:
2908:
2905:
2892:
2888:
2884:
2878:
2875:
2862:
2858:
2854:
2850:
2844:
2841:
2828:
2824:
2820:
2813:
2810:
2797:
2793:
2789:
2782:
2779:
2766:
2762:
2758:
2751:
2748:
2744:
2740:
2737:
2732:
2729:
2716:
2712:
2706:
2703:
2690:
2686:
2682:
2675:
2672:
2659:
2655:
2651:
2647:
2646:
2641:
2634:
2631:
2618:
2614:
2610:
2603:
2600:
2587:
2583:
2579:
2572:
2569:
2556:
2552:
2548:
2541:
2538:
2522:
2518:
2511:
2507:
2501:
2498:
2484:
2480:
2474:
2472:
2468:
2455:
2451:
2447:
2440:
2438:
2434:
2421:
2417:
2416:
2411:
2404:
2401:
2397:
2392:
2389:
2385:
2380:
2377:
2373:
2368:
2365:
2359:
2355:
2354:
2347:
2344:
2328:
2323:
2318:
2311:
2310:
2301:
2298:
2285:
2281:
2275:
2272:
2259:
2255:
2251:
2245:
2243:
2239:
2232:
2225:
2223:9781617293870
2219:
2215:
2211:
2206:
2194:
2190:
2188:9781491978504
2184:
2180:
2176:
2175:
2169:
2157:
2153:
2151:9781491980446
2147:
2143:
2139:
2138:
2132:
2120:
2116:
2114:9781492032632
2110:
2106:
2102:
2101:
2095:
2083:
2079:
2077:9781492078197
2073:
2069:
2065:
2064:
2058:
2057:
2052:
2047:
2043:
2040:
2038:
2035:
2033:
2030:
2029:
2025:
2014:
2009:
2007:
2005:
2001:
1993:
1986:
1976:
1967:
1958:
1955:
1947:
1945:
1938:
1936:
1934:
1930:
1924:Search Engine
1923:
1921:
1919:
1914:
1907:
1905:
1904:(OCT) scans.
1903:
1899:
1895:
1891:
1890:GE Healthcare
1884:
1879:
1874:
1871:
1868:
1865:
1864:
1863:
1861:
1857:
1853:
1849:
1845:
1841:
1836:
1828:
1826:
1824:
1815:
1813:
1811:
1807:
1802:
1798:
1794:
1786:
1784:
1781:
1773:
1768:
1766:
1759:
1757:
1755:
1751:
1746:
1739:
1737:
1735:
1728:TensorFlow.js
1727:
1725:
1723:
1719:
1715:
1711:
1707:
1703:
1699:
1695:
1694:Object Pascal
1691:
1687:
1683:
1679:
1675:
1671:
1667:
1663:
1659:
1656:
1651:
1648:
1640:
1635:
1633:
1631:
1627:
1623:
1615:
1613:
1611:
1607:
1603:
1599:
1595:
1591:
1587:
1579:
1577:
1575:
1571:
1562:
1560:
1558:
1554:
1550:
1546:
1538:
1536:
1534:
1526:
1524:
1517:
1515:
1512:
1507:
1500:
1495:
1493:
1491:
1487:
1483:
1475:
1473:
1471:
1462:
1460:
1458:
1454:
1446:
1444:
1442:
1437:
1435:
1431:
1427:
1422:
1420:
1416:
1412:
1407:
1405:
1401:
1397:
1393:
1389:
1385:
1381:
1377:
1373:
1369:
1363:
1355:
1353:
1350:
1347:
1345:
1340:
1338:
1334:
1331:. During the
1330:
1329:
1324:
1321:
1318:
1313:
1311:
1307:
1302:
1300:
1296:
1292:
1288:
1284:
1280:
1276:
1272:
1268:
1264:
1260:
1252:
1250:
1248:
1244:
1240:
1236:
1232:
1228:
1224:
1220:
1217:
1216:deep learning
1213:
1210:
1202:
1197:
1195:
1193:
1189:
1185:
1181:
1176:
1174:
1170:
1166:
1161:
1159:
1155:
1154:deep learning
1151:
1147:
1143:
1139:
1135:
1131:
1128:
1124:
1113:
1108:
1106:
1101:
1099:
1094:
1093:
1091:
1090:
1083:
1080:
1076:
1073:
1072:
1071:
1068:
1066:
1063:
1062:
1056:
1055:
1048:
1045:
1043:
1040:
1038:
1035:
1033:
1030:
1028:
1025:
1023:
1020:
1018:
1015:
1014:
1008:
1007:
1000:
997:
995:
992:
990:
987:
985:
982:
980:
977:
975:
972:
970:
967:
965:
962:
961:
955:
954:
947:
944:
942:
939:
937:
934:
932:
929:
928:
922:
921:
914:
911:
909:
906:
904:
903:Crowdsourcing
901:
899:
896:
895:
889:
888:
879:
876:
875:
874:
871:
869:
866:
864:
861:
859:
856:
855:
852:
847:
846:
838:
835:
833:
832:Memtransistor
830:
828:
825:
823:
820:
816:
813:
812:
811:
808:
806:
803:
799:
796:
794:
791:
789:
786:
784:
781:
780:
779:
776:
774:
771:
769:
766:
764:
761:
757:
754:
753:
752:
749:
745:
742:
740:
737:
735:
732:
730:
727:
726:
725:
722:
720:
717:
715:
714:Deep learning
712:
710:
707:
706:
703:
698:
697:
690:
687:
685:
682:
680:
678:
674:
672:
669:
668:
665:
660:
659:
650:
649:Hidden Markov
647:
645:
642:
640:
637:
636:
635:
632:
631:
628:
623:
622:
615:
612:
610:
607:
605:
602:
600:
597:
595:
592:
590:
587:
585:
582:
580:
577:
575:
572:
571:
568:
563:
562:
555:
552:
550:
547:
545:
541:
539:
536:
534:
531:
529:
527:
523:
521:
518:
516:
513:
511:
508:
507:
504:
499:
498:
491:
488:
486:
483:
481:
478:
476:
473:
471:
468:
466:
463:
461:
458:
456:
454:
450:
446:
445:Random forest
443:
441:
438:
436:
433:
432:
431:
428:
426:
423:
421:
418:
417:
410:
409:
404:
403:
395:
389:
388:
381:
378:
376:
373:
371:
368:
366:
363:
361:
358:
356:
353:
351:
348:
346:
343:
341:
338:
336:
333:
331:
330:Data cleaning
328:
326:
323:
321:
318:
316:
313:
311:
308:
306:
303:
301:
298:
296:
293:
292:
286:
285:
278:
275:
273:
270:
268:
265:
263:
260:
258:
255:
253:
250:
248:
245:
243:
242:Meta-learning
240:
238:
235:
233:
230:
228:
225:
223:
220:
218:
215:
214:
208:
207:
204:
199:
195:
191:
190:
182:
176:
172:
169:
166:
164:
160:
157:
154:
151:
149:
145:
142:
138:
134:
130:
126:
123:
121:
117:
114:
110:
106:
103:
99:
95:
85:
83:
79:
65:
61:
57:
54:
52:
48:
41:
36:
30:
19:
6623:
6557:
6362:Applications
6146:Hugging Face
6110:David Silver
5758:Audio–visual
5711:
5612:Applications
5591:Augmentation
5436:
5295:
5246:Apache SINGA
5241:Apache MXNet
5137:Google Pixel
4985:
4882:
4874:
4839:Competitions
4817:AlphaGo Zero
4770:Google Brain
4690:November 11,
4688:. Retrieved
4679:
4669:
4657:. Retrieved
4643:
4631:. Retrieved
4622:
4597:. Retrieved
4583:
4557:. Retrieved
4548:
4538:
4526:. Retrieved
4497:. Retrieved
4488:
4460:. Retrieved
4446:
4434:. Retrieved
4425:
4416:
4404:. Retrieved
4395:
4386:
4375:, retrieved
4371:the original
4358:
4332:. Retrieved
4323:
4314:
4304:November 10,
4302:. Retrieved
4293:
4284:
4272:. Retrieved
4263:
4239:. Retrieved
4230:
4206:. Retrieved
4197:
4171:. Retrieved
4162:
4138:. Retrieved
4129:
4105:. Retrieved
4096:
4087:
4075:. Retrieved
4066:
4057:
4045:. Retrieved
4036:
4027:
4015:. Retrieved
4006:
3997:
3985:. Retrieved
3976:
3967:
3957:February 18,
3955:. Retrieved
3944:
3934:
3924:February 18,
3922:. Retrieved
3908:
3898:February 18,
3896:. Retrieved
3885:
3875:
3865:February 18,
3863:. Retrieved
3849:
3837:. Retrieved
3826:
3817:
3807:February 13,
3805:. Retrieved
3794:
3785:
3777:
3770:. Retrieved
3759:
3749:
3739:February 18,
3737:. Retrieved
3723:
3713:December 11,
3711:. Retrieved
3700:
3690:
3680:February 18,
3678:. Retrieved
3667:
3657:
3645:. Retrieved
3636:
3627:
3615:. Retrieved
3606:
3597:
3585:. Retrieved
3576:
3567:
3555:. Retrieved
3546:
3537:
3525:. Retrieved
3516:
3490:. Retrieved
3481:
3472:
3460:. Retrieved
3425:
3415:
3403:. Retrieved
3394:
3385:
3373:. Retrieved
3364:
3340:. Retrieved
3331:
3322:
3310:. Retrieved
3301:
3277:. Retrieved
3249:
3242:
3230:. Retrieved
3221:
3197:. Retrieved
3188:
3162:. Retrieved
3153:
3129:. Retrieved
3115:
3103:. Retrieved
3073:. Retrieved
3064:
3055:
3043:. Retrieved
3034:
3024:
3012:. Retrieved
2998:
2986:. Retrieved
2977:
2967:
2957:February 12,
2955:. Retrieved
2946:
2937:
2925:. Retrieved
2917:Google Cloud
2916:
2907:
2895:. Retrieved
2886:
2877:
2865:. Retrieved
2856:
2849:Jouppi, Norm
2843:
2831:. Retrieved
2822:
2812:
2800:. Retrieved
2791:
2781:
2769:. Retrieved
2760:
2750:
2731:
2719:. Retrieved
2705:
2695:November 11,
2693:. Retrieved
2684:
2674:
2662:. Retrieved
2643:
2633:
2623:November 25,
2621:. Retrieved
2612:
2602:
2592:November 11,
2590:. Retrieved
2581:
2571:
2561:November 11,
2559:. Retrieved
2550:
2540:
2530:November 10,
2528:. Retrieved
2516:
2500:
2487:. Retrieved
2460:November 24,
2458:. Retrieved
2449:
2426:November 10,
2424:. Retrieved
2413:
2403:
2391:
2379:
2367:
2352:
2346:
2334:. Retrieved
2308:
2300:
2288:. Retrieved
2274:
2264:November 10,
2262:. Retrieved
2253:
2209:
2199:November 25,
2197:. Retrieved
2173:
2162:November 25,
2160:. Retrieved
2136:
2125:November 25,
2123:. Retrieved
2099:
2088:December 21,
2086:. Retrieved
2062:
1997:
1985:neural style
1984:
1951:
1942:
1927:
1911:
1908:Social media
1888:
1880:Applications
1838:
1823:Google Drive
1819:
1816:Google Colab
1790:
1777:
1769:Integrations
1763:
1747:
1743:
1731:
1652:
1644:
1619:
1590:convolutions
1583:
1566:
1542:
1530:
1521:
1504:
1479:
1466:
1450:
1438:
1423:
1408:
1365:
1351:
1348:
1341:
1326:
1314:
1310:edge devices
1303:
1256:
1206:
1177:
1165:Google Brain
1162:
1122:
1121:
989:PAC learning
676:
525:
520:Hierarchical
452:
406:
400:
56:Google Brain
51:Developer(s)
29:
6473:FlatBuffers
6294:Categories
6242:Autoencoder
6197:Transformer
6065:Alex Graves
6013:OpenAI Five
5917:IBM Watsonx
5539:Convolution
5517:Overfitting
5331:Proprietary
5233:Open source
5132:Google Labs
4958:Transformer
4659:November 4,
4633:November 4,
4599:November 4,
4559:November 6,
4528:November 4,
4499:November 4,
4462:November 4,
4334:November 6,
4274:November 4,
4241:November 4,
4208:November 6,
4173:November 2,
4140:November 1,
4107:November 1,
4077:October 28,
4047:November 6,
4017:November 6,
3987:October 10,
3839:January 20,
3647:November 6,
3617:November 6,
3587:November 6,
3557:November 6,
3527:October 28,
3492:November 4,
3405:November 6,
3375:November 6,
3342:November 4,
3312:November 4,
3279:November 4,
3232:November 4,
3199:November 4,
3164:November 4,
3065:os.mbed.com
2988:February 2,
2913:"Cloud TPU"
2398:, p. 2
2336:October 26,
1750:FlatBuffers
1610:max-pooling
1209:proprietary
873:Multi-agent
810:Transformer
709:Autoencoder
465:Naive Bayes
203:data mining
94:/tensorflow
92:/tensorflow
18:TensorBoard
6651:Categories
6584:ChromiumOS
6558:TensorFlow
6523:Kubernetes
6379:OpenRefine
6283:Technology
6136:EleutherAI
6095:Fei-Fei Li
6090:Yann LeCun
6003:Q-learning
5986:Decisional
5912:IBM Watson
5820:Midjourney
5712:TensorFlow
5559:Activation
5512:Regression
5507:Clustering
5347:IBM Watson
5296:TensorFlow
5223:Comparison
5059:Chinchilla
4986:TensorFlow
4884:The MANIAC
4489:TensorFlow
4361:, Google,
4264:TensorFlow
4231:TensorFlow
4198:TensorFlow
4163:TensorFlow
4130:TensorFlow
4097:TensorFlow
4067:TensorFlow
4037:TensorFlow
4007:pkg.go.dev
3772:August 14,
3637:TensorFlow
3607:TensorFlow
3547:TensorFlow
3517:TensorFlow
3482:TensorFlow
3395:TensorFlow
3365:TensorFlow
3332:TensorFlow
3302:TensorFlow
3222:TensorFlow
3189:TensorFlow
3154:TensorFlow
2551:TechCrunch
2506:Dean, Jeff
2322:1605.08695
2048:References
1840:Google JAX
1835:Google JAX
1829:Google JAX
1810:frameworks
1797:extensions
1787:Extensions
1734:JavaScript
1666:Javascript
1641:TensorFlow
1616:Optimizers
1555:(MSE) and
1527:Distribute
1488:and later
1388:arithmetic
1384:throughput
1370:(TPU), an
1344:JavaScript
1253:TensorFlow
1203:DistBelief
1184:JavaScript
1123:TensorFlow
858:Q-learning
756:Restricted
554:Mean shift
503:Clustering
480:Perceptron
408:regression
310:Clustering
305:Regression
179:tensorflow
141:JavaScript
101:Written in
82:Repository
73:2015-11-09
33:TensorFlow
6443:AngularJS
6384:Tesseract
6166:MIT CSAIL
6131:Anthropic
6100:Andrew Ng
5998:AlphaZero
5842:VideoPoet
5805:AlphaFold
5742:MindSpore
5696:SpiNNaker
5691:Memristor
5598:Diffusion
5574:Rectifier
5554:Batchnorm
5534:Attention
5529:Adversary
5321:MindSpore
5261:DeepSpeed
5077:VideoPoet
5018:Assistant
4912:AlphaStar
4906:AlphaFold
4852:Lee Sedol
4823:AlphaZero
4754:Google AI
3452:198931032
3269:980886715
2613:CSMonitor
2250:"Credits"
2233:Citations
2004:DeepDream
2002:software
1954:Carousell
1939:Education
1933:RankBrain
1844:framework
1806:libraries
1801:libraries
1793:libraries
1434:petaflops
1430:bandwidth
1426:teraflops
1419:petaflops
1415:teraflops
1227:Jeff Dean
1167:team for
1146:inference
1017:ECML PKDD
999:VC theory
946:ROC curve
878:Self-play
798:DeepDream
639:Bayes net
430:Ensembles
211:Paradigms
6599:Goobuntu
6543:OR-Tools
6369:Chromium
6355:Software
6274:Portals
6033:Auto-GPT
5865:Word2vec
5669:Hardware
5586:Datasets
5488:Concepts
5381:Category
5316:OpenVINO
5160:Category
5108:See also
5011:Chatbots
4918:AlphaDev
4798:Versions
4684:Archived
4653:Archived
4627:Archived
4593:Archived
4569:cite web
4553:Archived
4522:Archived
4493:Archived
4456:Archived
4436:June 18,
4430:Archived
4406:June 18,
4400:Archived
4377:June 18,
4328:Archived
4298:Archived
4268:Archived
4235:Archived
4202:Archived
4167:Archived
4134:Archived
4101:Archived
4071:Archived
4041:Archived
4011:Archived
3981:Archived
3951:Archived
3918:Archived
3892:Archived
3859:Archived
3833:Archived
3801:Archived
3766:Archived
3733:Archived
3707:Archived
3674:Archived
3641:Archived
3611:Archived
3581:Archived
3551:Archived
3521:Archived
3486:Archived
3462:July 25,
3456:Archived
3399:Archived
3369:Archived
3336:Archived
3306:Archived
3273:Archived
3226:Archived
3193:Archived
3158:Archived
3125:Archived
3099:Archived
3069:Archived
3039:Archived
3008:Archived
2982:Archived
2951:Archived
2921:Archived
2891:Archived
2861:Archived
2827:Archived
2796:Archived
2765:Archived
2739:Archived
2721:March 3,
2715:Archived
2689:Archived
2664:July 24,
2658:Archived
2617:Archived
2586:Archived
2555:Archived
2521:Archived
2489:June 27,
2483:Archived
2454:Archived
2420:Archived
2358:Archived
2327:Archived
2290:June 28,
2284:Archived
2258:Archived
2193:Archived
2156:Archived
2119:Archived
2082:Archived
2010:See also
1994:Research
1848:autograd
1604:, GELU,
1559:(BCE).
1496:Features
1447:Edge TPU
1396:training
1320:dataflow
1317:stateful
1231:refactor
1223:Alphabet
1142:training
440:Boosting
289:Problems
120:Platform
6619:Code-in
6612:Related
6589:Fuchsia
6548:Polymer
6528:LevelDB
6508:Guetzli
6478:Flutter
6468:Cpplint
6458:Blockly
6438:Angular
6415:Sawzall
6156:Meta AI
5993:AlphaGo
5977:PanGu-Σ
5947:ChatGPT
5922:Granite
5870:Seq2seq
5849:Whisper
5770:WaveNet
5765:AlexNet
5737:Flux.jl
5717:PyTorch
5569:Sigmoid
5564:Softmax
5429:General
5342:Core ML
5291:PyTorch
5170:Commons
5024:Sparrow
4952:WaveNet
4876:AlphaGo
4846:Fan Hui
4805:AlphaGo
4791:AlphaGo
4617:Xulin.
4363:Bibcode
3131:May 22,
3105:May 22,
3075:May 24,
3045:May 24,
3014:May 19,
2927:May 24,
2897:May 18,
2867:May 19,
2833:May 24,
2802:May 24,
2771:May 24,
2053:General
1913:Twitter
1885:Medical
1860:PyTorch
1714:Crystal
1682:Haskell
1626:ADAGRAD
1606:Sigmoid
1598:Softmax
1576:(IoU).
1563:Metrics
1490:PyTorch
1486:Chainer
1482:PyTorch
1390:(e.g.,
1328:tensors
1295:Android
1291:Windows
1198:History
1158:PyTorch
1022:NeurIPS
839:(ECRAM)
793:AlexNet
435:Bagging
174:Website
163:License
156:library
137:Android
133:Windows
71: (
6594:gLinux
6533:libvpx
6518:gVisor
6488:Gerrit
6400:Carbon
6347:Google
6171:Huawei
6151:OpenAI
6053:People
6023:MuZero
5885:Gemini
5880:Claude
5815:DALL-E
5727:Theano
5362:MATLAB
5301:Theano
5286:OpenNN
5281:ML.NET
5096:(2024)
5079:(2024)
5073:(2023)
5071:Gemini
5067:(2022)
5061:(2022)
5055:(2021)
5049:(2018)
5032:(2023)
5030:Gemini
5026:(2022)
5020:(2016)
4966:(2022)
4960:(2017)
4954:(2016)
4926:(2024)
4920:(2023)
4914:(2019)
4908:(2018)
4887:(2023)
4879:(2017)
4860:(2017)
4858:Ke Jie
4854:(2016)
4848:(2015)
4831:(2019)
4829:MuZero
4825:(2017)
4819:(2017)
4813:(2016)
4811:Master
4807:(2015)
4765:Google
3977:GitHub
3946:GitHub
3887:GitHub
3828:GitHub
3796:GitHub
3761:GitHub
3702:GitHub
3669:GitHub
3450:
3440:
3267:
3257:
3035:Medium
2978:Beebom
2887:Google
2823:Medium
2792:Medium
2761:Medium
2645:GitHub
2450:Medium
2220:
2185:
2148:
2111:
2074:
1948:Retail
1929:Google
1808:, and
1780:Python
1740:TFLite
1712:, and
1690:MATLAB
1672:, and
1655:Python
1628:, and
1572:, and
1539:Losses
1337:GitHub
1323:graphs
1190:, and
1180:Python
1169:Google
815:Vision
671:RANSAC
549:OPTICS
544:DBSCAN
528:-means
335:AutoML
105:Python
88:github
6513:Guice
6493:Guava
6483:Gears
6453:Bazel
6374:Gemma
6237:Mamba
6008:SARSA
5972:LLaMA
5967:BLOOM
5952:GPT-J
5942:GPT-4
5937:GPT-3
5932:GPT-2
5927:GPT-1
5890:LaMDA
5722:Keras
5339:Apple
5306:Torch
5271:Keras
5251:Caffe
5087:Other
5053:LaMDA
4974:Other
4899:Other
3448:S2CID
2685:Wired
2582:Slate
2524:(PDF)
2513:(PDF)
2415:Wired
2330:(PDF)
2317:arXiv
2313:(PDF)
2042:Keras
1856:NumPy
1774:Numpy
1722:Swift
1710:OCaml
1702:Scala
1686:Julia
1647:Keras
1580:TF.nn
1470:ARM's
1392:8-bit
1287:macOS
1283:Linux
1125:is a
1037:IJCAI
863:SARSA
822:Mamba
788:LeNet
783:U-Net
609:t-SNE
533:Fuzzy
510:BIRCH
129:macOS
125:Linux
6579:AOSP
6538:NaCl
6503:Gson
6498:gRPC
6448:Beam
6405:Dart
6161:Mila
5962:PaLM
5895:Bard
5875:BERT
5858:Text
5837:Sora
5311:ONNX
5266:Dlib
5094:Vids
5065:PaLM
5047:BERT
4964:Gato
4692:2015
4680:Vice
4661:2021
4635:2021
4601:2021
4575:link
4561:2021
4530:2021
4501:2021
4464:2021
4438:2022
4408:2022
4379:2022
4336:2021
4306:2018
4276:2021
4243:2021
4210:2021
4175:2021
4142:2021
4109:2021
4079:2021
4049:2021
4019:2021
3989:2018
3959:2018
3926:2018
3900:2018
3867:2018
3841:2023
3809:2020
3774:2019
3741:2018
3715:2018
3682:2018
3649:2021
3619:2021
3589:2021
3559:2021
3529:2021
3494:2021
3464:2023
3438:ISBN
3407:2021
3377:2021
3344:2021
3314:2021
3281:2021
3265:OCLC
3255:ISBN
3234:2021
3201:2021
3166:2021
3133:2020
3107:2020
3077:2019
3047:2019
3016:2017
2990:2019
2959:2018
2929:2019
2899:2017
2869:2016
2835:2019
2804:2019
2773:2019
2723:2024
2697:2015
2666:2017
2625:2015
2594:2015
2563:2015
2532:2015
2491:2018
2462:2019
2428:2015
2338:2020
2292:2018
2266:2015
2218:ISBN
2201:2019
2183:ISBN
2164:2019
2146:ISBN
2127:2019
2109:ISBN
2090:2020
2072:ISBN
1918:VSCO
1894:MRIs
1795:and
1720:and
1706:Rust
1674:Java
1622:ADAM
1602:RELU
1453:ASIC
1376:ASIC
1306:TPUs
1297:and
1275:SYCL
1273:and
1271:CUDA
1267:GPUs
1265:and
1263:CPUs
1192:Java
1144:and
1136:and
1132:for
1047:JMLR
1032:ICLR
1027:ICML
913:RLHF
729:LSTM
515:CURE
201:and
181:.org
148:Type
113:CUDA
90:.com
58:Team
6433:AMP
5902:NMT
5785:OCR
5780:HWR
5732:JAX
5686:VPU
5681:TPU
5676:IPU
5500:SGD
3430:doi
2650:doi
1852:XLA
1760:TFX
1692:,
1670:C++
1662:API
1299:iOS
1188:C++
1148:of
773:SOM
763:GAN
739:ESN
734:GRU
679:-NN
614:SDL
604:PGD
599:PCA
594:NMF
589:LDA
584:ICA
579:CCA
455:-NN
109:C++
6653::
6563:V8
6410:Go
4682:.
4678:.
4651:.
4625:.
4621:.
4609:^
4591:.
4571:}}
4567:{{
4551:.
4547:.
4520:.
4509:^
4491:.
4487:.
4472:^
4454:.
4424:.
4398:.
4394:.
4357:,
4344:^
4326:.
4322:.
4296:.
4292:.
4266:.
4262:.
4251:^
4233:.
4229:.
4218:^
4200:.
4196:.
4183:^
4165:.
4161:.
4150:^
4132:.
4128:.
4117:^
4099:.
4095:.
4069:.
4065:.
4039:.
4035:.
4009:.
4005:.
3979:.
3975:.
3949:.
3943:.
3890:.
3884:.
3825:.
3793:.
3776:.
3764:.
3758:.
3705:.
3699:.
3672:.
3666:.
3639:.
3635:.
3609:.
3605:.
3579:.
3575:.
3549:.
3545:.
3519:.
3515:.
3502:^
3484:.
3480:.
3454:.
3446:.
3436:.
3424:.
3397:.
3393:.
3367:.
3363:.
3352:^
3334:.
3330:.
3304:.
3300:.
3289:^
3271:.
3263:.
3224:.
3220:.
3209:^
3191:.
3187:.
3174:^
3156:.
3152:.
3141:^
3085:^
3067:.
3063:.
3037:.
3033:.
2980:.
2976:.
2949:.
2945:.
2919:.
2915:.
2885:.
2859:.
2855:.
2851:.
2825:.
2821:.
2794:.
2790:.
2763:.
2759:.
2687:.
2683:.
2656:.
2648:.
2642:.
2615:.
2611:.
2584:.
2580:.
2553:.
2549:.
2515:.
2481:.
2470:^
2452:.
2448:.
2436:^
2418:.
2412:.
2325:.
2282:.
2256:.
2252:.
2241:^
2191:.
2154:.
2117:.
2080:.
2006:.
1825:.
1724:.
1718:Go
1708:,
1704:,
1700:,
1696:,
1688:,
1684:,
1680:,
1678:C#
1668:,
1624:,
1600:,
1459:.
1443:.
1421:.
1346:.
1312:.
1301:.
1289:,
1285:,
1249:.
1186:,
1182:,
1160:.
1042:ML
139:,
135:,
131:,
127:,
111:,
107:,
6339:e
6332:t
6325:v
5415:e
5408:t
5401:v
5204:e
5197:t
5190:v
5118:"
5114:"
4746:e
4739:t
4732:v
4694:.
4663:.
4637:.
4603:.
4577:)
4563:.
4532:.
4503:.
4466:.
4440:.
4410:.
4365::
4338:.
4308:.
4278:.
4245:.
4212:.
4177:.
4144:.
4111:.
4081:.
4051:.
4021:.
3991:.
3961:.
3928:.
3902:.
3869:.
3843:.
3811:.
3743:.
3717:.
3684:.
3651:.
3621:.
3591:.
3561:.
3531:.
3496:.
3466:.
3432::
3409:.
3379:.
3346:.
3316:.
3283:.
3236:.
3203:.
3168:.
3135:.
3109:.
3079:.
3049:.
3018:.
2992:.
2961:.
2931:.
2901:.
2871:.
2837:.
2806:.
2775:.
2725:.
2699:.
2668:.
2652::
2627:.
2596:.
2565:.
2534:.
2495:,
2493:.
2464:.
2430:.
2340:.
2319::
2294:.
2268:.
2226:.
2203:.
2166:.
2129:.
2092:.
1698:R
1660:(
1596:(
1374:(
1111:e
1104:t
1097:v
677:k
526:k
453:k
411:)
399:(
75:)
20:)
Text is available under the Creative Commons Attribution-ShareAlike License. Additional terms may apply.
