本页面介绍深度学习相关的背景知识。
= 深度神经网络 =
深度神经网络，Deep Neural Networks，简称DNNNetworks，简称DNN。
[[智能与神经科学]]，深度学习借鉴神经科学的发现。 [[卷积神经网络]]，Convolutional Neural Networks，简称CNNNetworks，简称CNN。 [[循环神经网络]]，Recurrent Neural Networks，简称RNN。 [[人工神经网络的历史]]
历史：The rebirth of neural networks, ISCA 2010.
[http://pages.saclay.inria.fr/olivier.temam/homepage/ISCA2010web.pdf Rebirth_NN]
= 四个层面 =
{| class="wikitable"|-! 团队 !! Leader !! 说明|-| * 目标与功能|| : 语音识别、机器视觉、自然语言理解 || : 智能问答是综合以上功能的高级系统|-|* 核心技术|| : 特定算法、机器学习算法、深度神经网络 || |-| * 软件框架|| : TensorFlow /pyTorch /Torch /Caffe /Theano || |-| * 底层硬件|| : 可编程逻辑阵列 FPGA / 通用图形处理器 GPGPU / 通用处理器 CPU 群集 || |}
: 语音识别、机器视觉、自然语言理解== 国际研究 ==: 智能问答是综合以上功能的高级系统{| class="wikitable"|-* 核心技术! 团队 !! Leader !! 说明|-| [http: 特定算法、机器学习算法、深度神经网络//research.google.com/teams/brain/ Google Brain]|| ([http://research.google.com/pubs/jeff.html Jeffrey Dean]) || |-* 软件工具| [https://research.facebook.com/ai Facebook AI Research (FAIR)] || ([http://yann.lecun.com/ Yann LeCun]) || |-| [https: TensorFlow / Caffe / Torch * 底层硬件www.microsoft.com/en-us/research/group/dltc/ MSR Deep Learning Technology Center (DLTC)]|| ([https://www.microsoft.com/en-us/research/people/deng/ Li Deng]) || |-| [https: 可编程逻辑阵列 FPGA / 通用图形处理器 GPGPU / 通用处理器 CPU 群集www.openai.com/blog/ OpenAI]|| ([http://www.cs.toronto.edu/~ilya/ Ilya Sutskever]) || |}
== 框架工具 ==
{| class="wikitable"
|-
! 工具 !! 公司!! 链接 !! 说明
|-
| [https://www.tensorflow.org/ TensorFlow] || '''Google'''|| ([https://github.com/tensorflow/tensorflow Source Code]) || [http://download.tensorflow.org/paper/whitepaper2015.pdf TensorFlow_Whitepaper]
|-
| [http://pytorch.org/ pyTorch] [http://torch.ch/ Torch] || '''Facebook'''|| ([https://github.com/torch/torch7 Source Code]) || [https://github.com/facebook/fbcunn fbcunn]
|-
| [http://cntk.ai CNTK] || '''Microsoft'''|| ([https://github.com/microsoft/cntk Source Code]) ||
|-
| [http://mxnet.io/ MXNet] || '''[http://dmlc.ml/ DMLC]''' || ([https://github.com/dmlc/mxnet Source Code]) ||
|-
| [http://www.deeplearning.net/software/theano/ Theano] || '''Université de Montréal'''|| ([https://github.com/Theano/Theano/ Source Code]) ||
|-
| [http://www.paddlepaddle.org/ PaddlePaddle] || ''' Baidu'''|| ([https://github.com/PaddlePaddle/Paddle Source Code]) ||
|}
= 阅读材料 =
[[深度学习-入门导读]]
== 国际研究 ==
[http://research.google.com/teams/brain/ Google Brain]
([http://research.google.com/pubs/jeff.html Jeffrey Dean])
[https://research.facebook.com/ai Facebook AI Research (FAIR)]
([http://yann.lecun.com/ Yann LeCun])
[https://www.microsoft.com/en-us/research/group/dltc/ MSR Deep Learning Technology Center (DLTC)]
([https://www.microsoft.com/en-us/research/people/deng/ Li Deng])
[https://www.openai.com/blog/ OpenAI]
([http://www.cs.toronto.edu/~ilya/ Ilya Sutskever])
== 工具 ==
'''Google'''
[https://www.tensorflow.org/ TensorFlow]
([https://github.com/tensorflow/tensorflow Source Code])
[http://download.tensorflow.org/paper/whitepaper2015.pdf TensorFlow_Whitepaper]
'''Facebook'''
[http://torch.ch/ Torch]
([https://github.com/torch/torch7 Source Code])
[https://github.com/facebook/fbcunn fbcunn]
'''Microsoft'''
[http://cntk.ai CNTK]
([https://github.com/microsoft/cntk Source Code])
'''[http://dmlc.ml/ DMLC]'''
[http://mxnet.io/ MXNet]
([https://github.com/dmlc/mxnet Source Code])
'''Université de Montréal'''
[http://www.deeplearning.net/software/theano/ Theano]
([https://github.com/Theano/Theano/ Source Code])
''' Baidu'''
[http://www.paddlepaddle.org/ PaddlePaddle]
([https://github.com/PaddlePaddle/Paddle Source Code])