- 主页[http://www.cs.toronto.edu/~guerzhoy/tf_alexnet/]
- 代码[http://www.cs.toronto.edu/~guerzhoy/tf_alexnet/myalexnet.py]
- 模型参数 bvlc_alexnet.npy[https://drive.google.com/open?id=0B7Wy478uBsx8eTI4OTVOeGxtcVE]
- Deep Image Retrieval: Learning global representations for image search [https://arxiv.org/pdf/1604.01325.pdf]
- Learning from Small Sample Sets by Combining Unsupervised Meta-Training with CNNs [https://papers.nips.cc/paper/6408-learning-from-small-sample-sets-by-combining-unsupervised-meta-training-with-cnns]
- 手写数字识别[lstm_mnist_28x28x10.py]
- Caltech101分类-灰度[lstm_caltech_227x227x101L.py]
- 图片生成 -- DRAW: A Recurrent Neural Network For Image Generation by Gregor et al. (Review by Tim Cooijmans)[https://github.com/tensorflow/magenta/blob/master/magenta/reviews/draw.md]
- 序列生成 -- Generating Sequences with Recurrent Neural Networks by Graves. (Review by David Ha)[https://github.com/tensorflow/magenta/blob/master/magenta/reviews/summary_generation_sequences.md]
- 论文 [https://arxiv.org/pdf/1502.04623v2.pdf]
- 笔记 [https://github.com/tensorflow/magenta/blob/master/magenta/reviews/draw.md]
- 代码 [https://github.com/ericjang/draw]
- 笔记 Pixel Recurrent Neural Networks by Van den Oord et al. (Review by Kyle Kastner)[https://github.com/tensorflow/magenta/blob/master/magenta/reviews/pixelrnn.md]
- 代码 [https://github.com/carpedm20/pixel-rnn-tensorflow]
- 论文 [https://arxiv.org/abs/1601.06759]
- 论文 Matching Networks for One Shot Learning [https://arxiv.org/abs/1606.04080]
- 笔记 [https://github.com/karpathy/paper-notes/blob/master/matching_networks.md]
- 代码 code with tensorflow [https://github.com/zergylord/oneshot]
- 代码 code with theano [https://github.com/tristandeleu/ntm-one-shot]
- 双向lstm bidirectional-lstm 代码 [https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/3_NeuralNetworks/bidirectional_rnn.py]
- sequence to sequence lstm 笔记 [https://github.com/jxieeducation/DIY-Data-Science/blob/master/research/seq2seq.md]
- set to set lstm 论文 order matters sequence to sequence for sets [https://arxiv.org/abs/1511.06391]
- 笔记 Order Matters: Sequence To Sequence For Sets [https://lschacker.gitbooks.io/running-paper/content/order_matters_sequence_to_sequence_for_sets.html]
- pointer network 代码[https://github.com/pradyu1993/seq2set-keras] 讲解 [http://pradyu1993.github.io/2016/10/03/ptr-net-post.html]
- One-shot Learning with Memory-Augmented Neural Networks 论文 [https://arxiv.org/pdf/1605.06065v1.pdf] 代码 [https://github.com/tristandeleu/ntm-one-shot]
- pix2pix Image-to-Image Translation Using Conditional Adversarial Networks [https://arxiv.org/pdf/1611.07004v1.pdf]
- 代码 [https://github.com/yenchenlin/pix2pix-tensorflow]
- Unsupervised Image to Image Translation Networks [https://arxiv.org/abs/1701.02676]
##Reasoning, Attention, Memory
- 自然语言处理中的Attention Model:是什么及为什么 [http://blog.csdn.net/malefactor/article/details/50550211]
- Attention based model 是什么,它解决了什么问题?[https://www.zhihu.com/question/36591394]
- 一些attention的例子,图片分类,生成,生成主题 [http://www.cosmosshadow.com/ml/%E7%A5%9E%E7%BB%8F%E7%BD%91%E7%BB%9C/2016/03/08/Attention.html]
- attention机制 attention mechanisms with tensorflow [http://www.slideshare.net/KeonKim/attention-mechanisms-with-tensorflow]
- attention机制 论文 Effective Approaches to Attention-based Neural Machine Translation [http://www.aclweb.org/anthology/D15-1166]
- 论文相关视频 12- effective approaches to attention-based neural machine translation [https://www.youtube.com/watch?v=XvOKXJxDn1U][https://vimeo.com/162101582]
- attention机制 代码 [https://github.com/lmthang/nmt.matlab]
##Generative Adversarial Networks 网络
- Ian Goodfellow--2016talk [https://www.youtube.com/watch?v=HN9NRhm9waY]
- Ian Goodfellow--Review by Max Strakhov [https://github.com/tensorflow/magenta/blob/master/magenta/reviews/GAN.md]
- Improved Techniques for Training GANs [https://arxiv.org/abs/1606.03498]
- 各种GAN改进的概览--CGAN-LAPGAN-DCGAN-GRAN-VAEGAN-- [http://chuansong.me/n/317902651864]
- GAN相关的论文总结 [https://github.com/zhangqianhui/AdversarialNetsPapers]
- Image Completion with Deep Learning in TensorFlow ---- Brandon Amos [https://bamos.github.io/2016/08/09/deep-completion/]
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks[https://arxiv.org/abs/1511.06434]
- DCGAN - How does it work? [https://www.youtube.com/watch?v=VAeEt9df-hQ]
- DCGAN with SVHN dataset github code [https://github.com/shuyo/iir/blob/master/dnn/dcgan-svhn.py]
- 代码 [dcgan_svhn_32x32x3.py]
- 结果 [https://drive.google.com/open?id=0B7Wy478uBsx8ekhVbEVqeXU5cTA]
- 优化DCGAN网络 论文:Improved Techniques for Training GANs [https://arxiv.org/abs/1606.03498] 代码 [https://github.com/openai/improved-gan] \ppt
- GAN网络的终极优化Wasserstein GAN 论文[https://arxiv.org/abs/1701.07875] 分析笔记[https://zhuanlan.zhihu.com/p/25071913]
##Unsupervised Domain Adaptation
- 论文 Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptation [https://arxiv.org/pdf/1607.03516v2.pdf]
##Deep Belief Networks
##Deep Residual Networks
- He Kaiming----MSRA 2015 [https://github.com/KaimingHe/deep-residual-networks]
- He Kaiming----CVPR 2016 [https://www.youtube.com/watch?v=C6tLw-rPQ2o]
##Caltech101
- files: train28x28.tfrecords test28x28.tfrecords train.tfrecords test.tfrecords
- 生成脚本 [utils/save_dirs_to_tfrecords.py] [utils/save_dirs_to_tfrecords_28x28.py]
- google drive[https://drive.google.com/open?id=0B7Wy478uBsx8YWpLWEQyLVVQRjA]
##Omniglot
##生成艺术品和音乐 Magenta
- 主页 [https://github.com/tensorflow/magenta]
- 相关论文 [https://github.com/tensorflow/magenta/tree/master/magenta/reviews]
#Lecture
- Yann LeCun Lecture 1/8 Why Deep Learning ? [https://www.youtube.com/watch?v=ChLEJA6J2b8]
- Yann LeCun Lecture 2/8 Multilayered Networks and Gradient-based Backpropagation [https://www.youtube.com/watch?v=oX58hCamkwM]
- Yann LeCun Lecture 3/8 Deep Learning in Practice [https://www.youtube.com/watch?v=FWdybkCarv0]
- Yann LeCun Lecture 4/8 Convolutional Neural Networks [https://www.youtube.com/watch?v=LrUYRwAJXKM]
- Yann LeCun Lecture 5/8 Convolutional Networks and their Applications in Vision [https://www.youtube.com/watch?v=zHosOTMScnA]
- Yann LeCun Lecture 6/8 Recurrent Neural Networks and their Applications in NLP [https://www.youtube.com/watch?v=C-ChIA009zk]
- Yann LeCun Lecture 7/8 Reasoning, Attention, Memory [https://www.youtube.com/watch?v=TrV_PMPpQ6Q]
- Yann LeCun Lecture 8/8 Unsupervised Learning [https://www.youtube.com/watch?v=RftTFBmOrrY&t=5254s]
http://www.bayareadlschool.org Deep Learning School on September 24/25, 2016
- Foundations of Deep Learning (Hugo Larochelle, Twitter) - https://youtu.be/zij_FTbJHsk
- Deep Learning for Computer Vision (Andrej Karpathy, OpenAI) - https://youtu.be/u6aEYuemt0M
- Deep Learning for Natural Language Processing (Richard Socher, Salesforce) - https://youtu.be/oGk1v1jQITw
- TensorFlow Tutorial (Sherry Moore, Google Brain) - https://youtu.be/Ejec3ID_h0w
- Foundations of Unsupervised Deep Learning (Ruslan Salakhutdinov, CMU) - https://youtu.be/rK6bchqeaN8
- Nuts and Bolts of Applying Deep Learning (Andrew Ng) - https://youtu.be/F1ka6a13S9I
- Deep Reinforcement Learning (John Schulman, OpenAI) - https://youtu.be/PtAIh9KSnjo
- Theano Tutorial (Pascal Lamblin, MILA) - https://youtu.be/OU8I1oJ9HhI
- Deep Learning for Speech Recognition (Adam Coates, Baidu) - https://youtu.be/g-sndkf7mCs
- Torch Tutorial (Alex Wiltschko, Twitter) - https://youtu.be/L1sHcj3qDNc
- Sequence to Sequence Deep Learning (Quoc Le, Google) - https://youtu.be/G5RY_SUJih4
- Foundations and Challenges of Deep Learning (Yoshua Bengio) - https://youtu.be/11rsu_WwZTc
- 主页 [https://bcourses.berkeley.edu/courses/1453965/pages/cs294-129-designing-visualizing-and-understanding-deep-neural-networks]
- youtube playlist [https://www.youtube.com/playlist?list=PLkFD6_40KJIxopmdJF_CLNqG3QuDFHQUm]
- 主页 https://berkeley-deep-learning.github.io/cs294-dl-f16/
- Oriol Vinyals: Sequences and one-shot learning 相关视频 Stanford Seminar - Recent Advances in Deep Learning [https://www.youtube.com/watch?v=UAq961jQjYg]
##周莫烦 python和tensorflow的快速教程
- youtube playlist [https://www.youtube.com/playlist?list=PLXO45tsB95cKI5AIlf5TxxFPzb-0zeVZ8]
- udacity 经典课程 [https://classroom.udacity.com/courses/ud730/lessons/6370362152/concepts/63798118150923#]
##Reinforcement learning by David Silver ---- Deepmind
- youtube playlist [https://www.youtube.com/playlist?list=PL7-jPKtc4r78-wCZcQn5IqyuWhBZ8fOxT]
- Lecture 笔记和课件 [http://www0.cs.ucl.ac.uk/staff/d.silver/web/Teaching.html]