作者：osforscience
编译：ronghuaiyang

导读

来自github的非常有针对性的深度学习资源，和其他的资源不同，既照顾了通用性，又照顾了不同的领域，覆盖非常广，非常的全面，有论文，有代码，有书，有博客，还有课程。

介绍

这个项目的目的是为开发人员和研究人员提供一个寻找关于深度学习的有用资源的捷径。

动机

这个开源项目有许多不同的动机。

这个开源项目的重点在哪里？

还有其他类似的repo与这个类似，而且非常全面和有用，老实说，它们让我思考是否有必要使用这个repo！

这个repo的重点是，资源是有针对性的。资源的组织使得用户可以很容易地找到他/她正在寻找的东西。我们把资源分成了很多类别，一开始你可能会头疼！！！然而，如果你知道正在定位的位置，就很容易找到最相关的资源。即使有人不知道要寻找什么，在开始时，会提供最通用的资源。

论文

部分与深度学习领域相关的论文。

模型

卷积神经网络

Imagenet classification with deep convolutional neural networks :[Paper][Code]
Convolutional Neural Networks for Sentence Classification : [Paper][Code]
Large-scale Video Classification with Convolutional Neural Networks : [Paper][Project Page]
Learning and Transferring Mid-Level Image Representations using Convolutional Neural Networks : [Paper]
Deep convolutional neural networks for LVCSR : [Paper]
Face recognition: a convolutional neural-network approach : [Paper]

循环神经网络

An empirical exploration of recurrent network architectures : [Paper][Code]
LSTM: A search space odyssey : [Paper][Code]
On the difficulty of training recurrent neural networks : [Paper][Code]
Learning to forget: Continual prediction with LSTM : [Paper]

自动编码器

Extracting and composing robust features with denoising autoencoders : [Paper]
Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion: [Paper][Code]
Adversarial Autoencoders : [Paper][Code]
Autoencoders, Unsupervised Learning, and Deep Architectures : [Paper]
Reducing the Dimensionality of Data with Neural Networks : [Paper][Code ]

生成模型

Exploiting generative models discriminative classifiers : [Paper]
Semi-supervised Learning with Deep Generative Models : [Paper][Code]
Generative Adversarial Nets : [Paper][Code]
Generalized Denoising Auto-Encoders as Generative Models : [Paper]
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks : [Paper][Code]

概率模型

Stochastic Backpropagation and Approximate Inference in Deep Generative Models: [Paper]
Probabilistic models of cognition: exploring representations and inductive biases : [Paper]
On deep generative models with applications to recognition : [Paper]

核心

优化器

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift : [Paper]
Dropout: A Simple Way to Prevent Neural Networks from Overfitting : [Paper]
Training Very Deep Networks : [Paper]
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification : [Paper]
Large Scale Distributed Deep Networks : [Paper]

表示学习

Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks : [Paper][Code]
Representation Learning: A Review and New Perspectives : [Paper]
InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets : [Paper][Code]

理解和迁移学习

Learning and Transferring Mid-Level Image Representations using Convolutional Neural Networks : [Paper]
Distilling the Knowledge in a Neural Network : [Paper]
DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition : [Paper][
How transferable are features in deep neural networks? : [Paper][Code]

强化学习

Human-level control through deep reinforcement learning : [Paper][Code]
Playing Atari with Deep Reinforcement Learning : [Paper][Code]
Continuous control with deep reinforcement learning : [Paper][Code]
Deep Reinforcement Learning with Double Q-Learning : [Paper][Code]
Dueling Network Architectures for Deep Reinforcement Learning : [Paper][Code]

应用

图像识别

Deep Residual Learning for Image Recognition : [Paper][Code]
Very Deep Convolutional Networks for Large-Scale Image Recognition : [Paper]
Multi-column Deep Neural Networks for Image Classification : [Paper]
DeepID3: Face Recognition with Very Deep Neural Networks : [Paper]
Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps : [Paper][Code]
Deep Image: Scaling up Image Recognition : [Paper]
Long-Term Recurrent Convolutional Networks for Visual Recognition and Description : [Paper][Code]
3D Convolutional Neural Networks for Cross Audio-Visual Matching Recognition : [Paper][Code]

物体识别

ImageNet Classification with Deep Convolutional Neural Networks : [Paper]
Learning Deep Features for Scene Recognition using Places Database : [Paper]
Scalable Object Detection using Deep Neural Networks : [Paper]
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks: [Paper][Code]
OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks : [Paper][Code]
CNN Features Off-the-Shelf: An Astounding Baseline for Recognition : [Paper]
What is the best multi-stage architecture for object recognition? : [Paper]

行为识别

Long-Term Recurrent Convolutional Networks for Visual Recognition and Description : [Paper]
Learning Spatiotemporal Features With 3D Convolutional Networks : [Paper][Code]
Describing Videos by Exploiting Temporal Structure : [Paper][Code]
Convolutional Two-Stream Network Fusion for Video Action Recognition: [Paper][Code]
Temporal segment networks: Towards good practices for deep action recognition : [Paper][Code]

标题生成

Show, Attend and Tell: Neural Image Caption Generation with Visual Attention : [Paper][Code]
Mind’s Eye: A Recurrent Visual Representation for Image Caption Generation : [Paper]
Generative Adversarial Text to Image Synthesis : [Paper][Code]
Deep Visual-Semantic Al60ignments for Generating Image Descriptions : [Paper][Code]
Show and Tell: A Neural Image Caption Generator : [Paper][Code]

自然语言处理

Distributed Representations of Words and Phrases and their Compositionality : [Paper][Code]
Efficient Estimation of Word Representations in Vector Space : [Paper][Code]
Sequence to Sequence Learning with Neural Networks : [Paper][Code]
Neural Machine Translation by Jointly Learning to Align and Translate : [Paper][Code]
Get To The Point: Summarization with Pointer-Generator Networks : [Paper][Code]
Attention Is All You Need : [Paper][Code]
Convolutional Neural Networks for Sentence Classification : [Paper][Code]

语音技术

Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups : [Paper]
Towards End-to-End Speech Recognition with Recurrent Neural Networks: [Paper]
Speech recognition with deep recurrent neural networks : [Paper]
Fast and Accurate Recurrent Neural Network Acoustic Models for Speech Recognition : [Paper]
Deep Speech 2 : End-to-End Speech Recognition in English and Mandarin : [Paper][Code]
A novel scheme for speaker recognition using a phonetically-aware deep neural network : [Paper]
Text-Independent Speaker Verification Using 3D Convolutional Neural Networks : [Paper][Code]

数据集

图像

通用

MNIST 手写数字: [Link]

人脸

Face Recognition Technology (FERET) FERET项目的目标是开发自动人脸识别能力，可用于协助安全、情报和执法人员履行其职责: [Link]
The CMU Pose, Illumination, and Expression (PIE) Database of Human Faces 从2000年10月到12月，我们收集了68人的41368张图片： [Link]
YouTube Faces DB 该数据集包含3,425个视频，涉及1,595个不同的人。所有的视频都是从YouTube上下载的。每个主题平均提供2.15个视频: [Link]
Grammatical Facial Expressions Data Set 用于帮助自动分析面部表情: [Link]
FaceScrub 数据集包含530人的10万多张面部图像: [Link]
IMDB-WIKI 50万以上贴有年龄和性别标签的面部照片: [Link]
FDDB 人脸检测数据集于benchmark: [Link]

物体识别

COCO : [Link]
ImageNet : [Link]
Open Images Dataset Open Images是一个包含大约900万张图像的数据集，这些图像已经用图像级别的标签和物体边界框进行了标注： [Link]
Caltech-256 Object Category Dataset 一个大型的物体分类数据集: [Link]
Pascal VOC dataset 一个大型的分类任务数据集: [Link]
CIFAR 10 / CIFAR 100 CIFAR-10数据集由10个类中的60000张32×32彩色图像组成。CIFAR-100与CIFAR-10类似，但它有100个类，每个类包含600张图像: [Link]

行为识别

HMDB 一个大型人体运动数据库: [Link]
MHAD 伯克利多模态人类行为数据库: [Link]
UCF101 – Action Recognition Data Set UCF101是一组现实动作视频的动作识别数据集，从YouTube上收集，共有101个动作类别。这个数据集是UCF50数据集的扩展，UCF50数据集有50个行为类别：[Link]
THUMOS Dataset 用于行为分类的大型数据集: [Link]
ActivityNet 人类活动理解的大型视频基准: [Link]

文本和自然语言处理

通用

1 Billion Word Language Model Benchmark: 该项目的目的是为语言建模实验提供一个标准的训练和测试设置: [Link]
Common Crawl: 通用抓取语料库包含过去7年收集的pb级数据。它包含原始网页数据、提取的元数据和文本提取: [Link]
Yelp Open Dataset: Yelp商业、评论和用户数据的子集，用于个人、教育和学术目的: [Link]

文本分类

20 newsgroups 20个新闻组数据集是大约20,000个新闻组文档的集合，(几乎)均匀地分在20个不同的新闻组中: [Link]
Broadcast News 1996年的广播新闻讲话语料库包括美国广播公司、美国有线电视新闻网和CSPAN电视网以及美国国家公共广播电台和PRI电台的104小时广播，并附有相应的文字记录: [Link]
The wikitext long term dependency language modeling dataset: 从维基百科上的一组经过验证的好文章和特色文章中提取的超过1亿个标记的集合: [Link]

问答

Question Answering Corpus 由Deep Mind和Oxford提供，这是两个新语料库，包含了来自CNN和每日邮报网站的大约100万篇新闻报道。 [Link]
Stanford Question Answering Dataset (SQuAD) 由一组维基百科文章上的众筹工作者提出的问题组成: [Link]
Amazon question/answer data 包含来自Amazon的问答数据，总计约140万个已回答的问题： [Link]

情感分析

Multi-Domain Sentiment Dataset 包含了从Amazon.com上获取的许多产品类型的产品评论: [Link]
Stanford Sentiment Treebank Dataset 是第一个完全标记解析树语料库，它允许对情感在语言中的构成效果进行完整的分析: [Link]
Large Movie Review Dataset: 这是一个用于二元情绪分类的数据集: [Link]

机器翻译

Aligned Hansards of the 36th Parliament of Canada 数据集包含130万对对齐的文本块：[Link]
Europarl: A Parallel Corpus for Statistical Machine Translation 数据集提取自欧洲议会议事录：[Link]

汇总

Legal Case Reports Data Set 4000个法律案例的文本语料库，用于自动汇总和引文分析： [Link]

语音技术

TIMIT Acoustic-Phonetic Continuous Speech Corpus TIMIT语音语料库的设计目的是为语音声学研究和自动语音识别系统的开发与评估提供语音数据: [Link]
LibriSpeech LibriSpeech是由Vassil Panayotov在Daniel Povey的帮助下编写的一个大约1000小时16kHz的英语演讲语料库: [Link]
VoxCeleb 一个大规模视频音频数据集：[Link]
NIST Speaker Recognition: [Link]

课程

Machine Learning by Stanford on Coursera : [Link]
Neural Networks and Deep Learning Specialization by Coursera: [Link]
Intro to Deep Learning by Google: [Link]
Introduction to Deep Learning by CMU: [Link]
NVIDIA Deep Learning Institute by NVIDIA: [Link]
Convolutional Neural Networks for Visual Recognition by Stanford: [Link]
Deep Learning for Natural Language Processing by Stanford: [Link]
Deep Learning by fast.ai: [Link]
Course on Deep Learning for Visual Computing by IITKGP: [Link]

书籍

Deep Learning by Ian Goodfellow: [Link]
Neural Networks and Deep Learning : [Link]
Deep Learning with Python: [Link]
Hands-On Machine Learning with Scikit-Learn and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems: [Link]

博客

Colah’s blog: [Link]
Andrej Karpathy blog: [Link]
The Spectator Shakir’s Machine Learning Blog: [Link]
WILDML: [Link]
Distill blog It is more like a journal than a blog because it has a peer review process and only accepyed articles will be published on that.: [Link]
BAIR Berkeley Artificial Inteliigent Research: [Link]
Sebastian Ruder’s blog: [Link]
inFERENCe: [Link]
i am trask A Machine Learning Craftsmanship Blog: [Link]

指南

Deep Learning Tutorials: [Link]
Deep Learning for NLP with Pytorch by Pytorch: [Link]
Deep Learning for Natural Language Processing: Tutorials with Jupyter Notebooksby Jon Krohn: [Link]