TensorFlow

TensorFlow
Developer(s) Google Brain Team[1]
Initial release November 9, 2015 (2015-11-09)
Stable release 0.8.0[2]
Development status Active
Written in Python, C++
Platform Linux, Mac OS X
Type Machine Learning Library
License Apache 2.0 open source license
Website tensorflow.org

TensorFlow is an open source software library for machine learning in various kinds of perceptual and language understanding tasks.[3] It is a second-generation API which is currently used for both research and production by 50[3]:min 0:15/2:17 different teams in dozens[4]:p.2 of commercial Google products, such as speech recognition, Gmail, Google Photos, and Search.[3]:0:26/2:17 These teams had previously used DistBelief, a first-generation API. TensorFlow was originally developed by the Google Brain team for Google's research and production purposes and later released under the Apache 2.0 open source license on November 9, 2015.[1][5]

History

DistBelief

Starting in 2011, Google Brain built DistBelief as their first-generation, proprietary, machine learning system. More than 50 teams at Google and other Alphabet companies have deployed DistBelief's deep learning neural networks in Google's commercial products, including Google Search, Google Voice Search, advertising, Google Photos, Google Maps, Google Street View, Google Translate, and YouTube.[4][6] Google assigned computer scientists, such as Dr. Geoffrey Hinton and Dr. Jeff Dean, to simplify and refactor the codebase of DistBelief into a faster, more robust application-grade library, which became TensorFlow.[7] In 2009, the team led by Hinton was able to reduce the amount of errors in neural networks which used DistBelief, by a substantial amount; this breakthrough was made possible by Hinton's scientific breakthroughs in generalized backpropagation. Most notably, Hinton's breakthrough directly led to reducing errors in Google’s speech recognition software by at least 25 percent.[8]

TensorFlow

TensorFlow is Google Brain's second generation machine learning system, with a reference implementation released as open source software on November 9, 2015. While the reference implementation runs on single devices, TensorFlow can run on multiple CPUs and GPUs [9] (with optional CUDA extensions for general-purpose computing on graphics processing units). It runs on 64-bit Linux or Mac OS X desktop or server systems, as well as on mobile computing platforms, including Android and Apple's iOS. TensorFlow computations are expressed as stateful dataflow graphs. Many teams at Google have migrated from DistBelief to TensorFlow for research and production uses.[4]:p.2 This library of algorithms originated from Google's need to instruct computer systems, known as neural networks, to learn and reason similarly to how humans do, so that new applications can be derived which are able to assume roles and functions previously reserved only for capable humans; the name TensorFlow itself derives from the operations which such neural networks perform on multidimensional data arrays. These multidimensional arrays are referred to as "tensors" but this concept is not identical to the mathematical concept of tensors.[10] The purpose is to train neural networks to detect and decipher patterns and correlations.

Features

TensorFlow provides a Python API, as well as a less documented C/C++ API.

Applications

Among the broad spectrum of applications TensorFlow is the foundation for, it has been successfully implemented in automated image captioning software, such as DeepDream.[11] Google officially implemented RankBrain on 26 October 2015, backed by TensorFlow, RankBrain now handles a substantial number of search queries, replacing and supplementing traditional static algorithm based search results.[12]

See also

References

  1. 1 2 "Credits". TensorFlow.org. Retrieved 10 November 2015.
  2. ↑ https://www.tensorflow.org/versions/r0.8/get_started/os_setup.html#download-and-setup
  3. 1 2 3 "TensorFlow: Open source machine learning" "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
  4. 1 2 3 Dean, Jeff; Monga, Rajat; et al. (November 9, 2015). "TensorFlow: Large-scale machine learning on heterogeneous systems" (PDF). TensorFlow.org. Google Research. Retrieved 10 November 2015.
  5. ↑ Metz, Cade (November 9, 2010). "Google Just Open Sourced TensorFlow, Its Artificial Intelligence Engine". Wired. Retrieved 10 November 2015.
  6. ↑ Perez, Sarah (November 9, 2015). "Google Open-Sources The Machine Learning Tech Behind Google Photos Search, Smart Reply And More". TechCrunch. Retrieved 11 November 2015.
  7. ↑ Oremus, Will (November 11, 2015). "What Is TensorFlow, and Why Is Google So Excited About It?". Slate. Retrieved 11 November 2015.
  8. ↑ Ward-Bailey, Jeff (November 25, 2015). "Google chairman: We’re making 'real progress' on artificial intelligence". CSMonitor. Retrieved 25 November 2015.
  9. ↑ Metz, Cade (November 10, 2015). "TensorFlow, Google's Open Source AI , Points to a Fast-Changing Hardware World". Wired. Retrieved 11 November 2015.
  10. ↑ "Tensor". PlanetMath. Retrieved 14 February 2016.
  11. ↑ Byrne, Michael (November 11, 2015). "Google Offers Up Its Entire Machine Learning Library as Open-Source Software". Vice. Retrieved 11 November 2015.
  12. ↑ Woollaston, Victoria (November 25, 2015). "Google releases TensorFlow - Search giant makes its artificial intelligence software available to the public". DailyMail. Retrieved 25 November 2015.

External links

This article is issued from Wikipedia - version of the Wednesday, April 27, 2016. The text is available under the Creative Commons Attribution/Share Alike but additional terms may apply for the media files.