深度学习赞表¶

免费在线书籍¶

深度学习作者 Yoshua Bengio, Ian Goodfellow 和 Aaron Courville (05/07/2015)
神经网络与深度学习作者 Michael Nielsen (Dec 2014)
深度学习作者 Microsoft Research (2013)
深度学习教程作者 LISA lab, University of Montreal (Jan 6 2015)
神经交谈作者 Andrej Karpathy : numpy-based RNN/LSTM implementation
遗传算法介绍
人工智能：现代方法
神经网络的深度学习：概述

课程¶

机器学习 - 斯坦福大学作者 Andrew Ng in Coursera (2010-2014)
机器学习 - 加州理工学院作者 Yaser Abu-Mostafa (2012-2014)
机器学习 - 卡耐基梅隆大学作者 Tom Mitchell (Spring 2011)
机器学习的神经网络作者 Geoffrey Hinton in Coursera (2012)
神经网络课程作者舍布鲁克大学的 Hugo Larochelle (2013)
深度学习课程作者 CILVR lab @ NYU (2014)
A.I - 伯克利作者 Dan Klein and Pieter Abbeel (2013)
A.I - 麻省理工学院作者 Patrick Henry Winston (2010)
愿景和学习 - 电脑和大脑作者 Shimon Ullman, Tomaso Poggio, Ethan Meyers @ MIT (2013)
用于视觉识别的卷积神经网络 - 斯坦福大学作者 Fei-Fei Li, Andrej Karpathy (2017)
神经网络 - usherbrooke
机器学习 - 牛津 (2014-2015)
深度学习 - Nvidia (2015)
暑期毕业生：深度学习，特色学习作者 Geoffrey Hinton, Yoshua Bengio, Yann LeCun, Andrew Ng, Nando de Freitas 和其他几个 @ IPAM, UCLA (2012)
深度学习 - Udacity / Google 作者 Vincent Vanhoucke and Arpan Chakraborty (2016)
深度学习 - UWaterloo 作者 Prof. Ali Ghodsi at University of Waterloo (2015)
统计机器学习 - CMU 作者 Prof. Larry Wasserman
深度学习课程作者 Yann LeCun (2016)
设计，可视化和理解深度神经网络 - 加州大学伯克利分校
UVA 深度学习课程 MSc in Artificial Intelligence for the University of Amsterdam.
麻省理工学院 6.S094：自驾车深度学习
麻省理工学院 6.S191：深度学习简介
伯克利 CS 294：深度强化学习
运动视频课程中的凯拉斯
编码的实用深度学习作者 Jeremy Howard - Fast.ai
深度学习简介作者 Prof. Bhiksha Raj (2017)
自然语言处理的深度学习 - 斯坦福大学

视频和讲座¶

如何创造一个心灵作者 Ray Kurzweil
深度学习，自学习和无监督特征学习作者 Andrew Ng
深度学习的最新进展作者 Geoff Hinton
深度学习的不合理有效性作者 Yann LeCun
表象的深刻学习作者 Yoshua bengio
分层时间记忆的原理作者 Jeff Hawkins
机器学习讨论组 - 深度学习与斯坦福大学人工智能实验室作者 Adam Coates
深入学习让世界感悟作者 Adam Coates
解开无监督的特征学习作者 Adam Coates
视觉感知与深度学习作者 Yann LeCun
下一代神经网络作者 Geoffrey Hinton at GoogleTechTalks
可以学习的电脑的美妙和可怕的含义作者 Jeremy Howard at TEDxBrussels
无监督深度学习 - 斯坦福大学作者 Andrew Ng in Stanford (2011)
自然语言处理作者 Chris Manning in Stanford
深度神经网络初学者指南作者 Natalie Hammel and Lorraine Yurshansky
深度学习：来自大数据的智能作者 Steve Jurvetson (and panel) at VLAB in Stanford.
人工神经网络与深度学习简介作者 Leo Isikdogan at Motorola Mobility HQ
NIPS 2016 讲座和研讨会视频 - NIPS 2016

论文¶

你也可以从这里找到引用最多的深度学习论文

教程¶

研究人员¶

网站¶

数据集¶

[MNIST]（http://yann.lecun.com/exdb/mnist/）手写的数字
Google House Numbers 来自街景
CIFAR-10 and CIFAR-100
IMAGENET
微小的图像 80 万张小图片 6
Flickr 数据 100 Million Yahoo dataset
伯克利分割数据集 500
加州大学欧文分校机器学习库
Flickr 8k
Flickr 30k
Microsoft COCO
VQA
Image QA
AT&T Laboratories Cambridge face database
AVHRR Pathfinder
Air Freight - 空运数据集是一个光线跟踪的图像序列，以及基于纹理特征的地面真实分割。 ,（455 图像+ GT，每个 160x120 像素）。 ,（格式：PNG）
阿姆斯特丹对象图像库 - ALOI 是为科学目的记录的一千个小物体的彩色图像集合。,为了捕捉对象记录中的感觉变化，我们系统地改变每个对象的视角，照明角度和照明颜色，并且另外捕获宽基线立体图像。我们记录了每个物体的上百张图像，共收集了 110,250 张图像。 ,（格式：png）
注明的脸，手，心脏和肉的图像 - 大多数图像和注释都是使用 AAM-API 进行各种 ASM / AAM 分析的补充。 ,（格式：bmp，asf）
图像分析和计算机图形学
大型时尚（DeepFashion）数据库 - 包含超过 800,000 种不同的时尚形象。,该数据集中的每个图像都标有 50 个类别，1,000 个描述性属性，边界框和服装标志
布朗大学刺激 - 各种数据集，包括 geons，对象和“greebles”。,适用于测试识别算法。 ,（格式：图片）
商场和公共空间行为的 CAVIAR 视频序列 - 在 90 个不同人类活动序列中的 90K 视频帧，具有检测和行为分类的 XML 基本事实（格式：MPEG2 和 JPEG）
Machine Vision Unit
Fashion-MNIST -MNIST 就像时尚产品数据集，由 60,000 个示例的训练集和 10,000 个示例的测试集组成。Each example is a 28x28 grayscale image, associated with a label from 10 classes.
CCITT 传真标准图像 - 8 images (Formats: gif)
CMU CIL 的立体声数据与地面真相 - 3 sets of 11 images, including color tiff images with spectroradiometry (Formats: gif, tiff)
CMU PIE 数据库 - A database of 41,368 face images of 68 people captured under 13 poses, 43 illuminations conditions, and with 4 different expressions.
CMU VASC 图像数据库 - Images, sequences, stereo pairs (thousands of images) (Formats: Sun Rasterimage)
加州理工图像数据库 - about 20 images - mostly top-down views of small objects and toys. (Formats: GIF)
哥伦比亚 - 乌得勒支反射和纹理数据库 - Texture and reflectance measurements for over 60 samples of 3D texture, observed with over 200 different combinations of viewing and illumination directions. (Formats: bmp)
计算颜色恒常性数据 - A dataset oriented towards computational color constancy, but useful for computer vision in general. It includes synthetic data, camera sensor data, and over 700 images. (Formats: tiff)
计算机视觉实验室
视觉对象类挑战 2012 年 (VOC2012) - VOC2012 dataset containing 12k images with 20 annotated classes for object detection and segmentation.
基于内容的图像检索数据库 - 11 sets of color images for testing algorithms for content-based retrieval. Most sets have a description file with names of objects in each image. (Formats: jpg)
高效的基于内容的检索组
打开图像数据集 - Open Images is a dataset of ~9 million URLs to images that have been annotated with labels spanning over 6000 categories.
密集采样视图领域 - Densely sampled view spheres - upper half of the view sphere of two toy objects with 2500 images each. (Formats: tiff)
计算机科学七（图形系统）
YouTube-8M 数据集 - YouTube-8M is a large-scale labeled video dataset that consists of 8 million YouTube video IDs and associated labels from a diverse vocabulary of 4800 visual entities.
Digital Embryos - Digital embryos are novel objects which may be used to develop and test object recognition systems. They have an organic appearance. (Formats: various formats are available on request)
明尼苏达大学视觉实验室的大学
萨尔瓦多胃肠视频内窥镜 - Images and Videos of his-res of studies taken from Gastrointestinal Video endoscopy. (Formats: jpg, mpg, gif)
FG-NET 面部老化数据库 - Database contains 1002 face images showing subjects at different ages. (Formats: jpg)
FVC2000 指纹数据库 - FVC2000 is the First International Competition for Fingerprint Verification Algorithms. Four fingerprint databases constitute the FVC2000 benchmark (3520 fingerprints in all).
生物识别系统实验室 - University of Bologna
脸部和手势图像和图像序列 - Several image datasets of faces and gestures that are ground truth annotated for benchmarking
德语 Fingerspelling 数据库 - The database contains 35 gestures and consists of 1400 image sequences that contain gestures of 20 different persons recorded under non-uniform daylight lighting conditions. (Formats: mpg,jpg)
语言处理和模式识别
DeepMind QA 语料库 - Textual QA corpus from CNN and DailyMail. More than 300K documents in total. Paper for reference.
格罗宁根自然图象数据库 - 4000+ 1536x1024 (16 bit) calibrated outdoor images (Formats: homebrew)
ICG 测试室序列 - 2 turntable sequences from ifferent viewing heights, 36 images each, resolution 1000x750, color (Formats: PPM)
计算机图形学与视觉研究所
计算机视觉和控制中心
IEN 图像库 - 1000+ images, mostly outdoor sequences (Formats: raw, ppm)
INRIA 的 Syntim 图像数据库 - 15 color image of simple objects (Formats: gif)
INRIA
INRIA 的 Syntim 立体声数据库 - 34 calibrated color stereo pairs (Formats: gif)
图像分析实验室 - Images obtained from a variety of imaging modalities -- raw CFA images, range images and a host of "medical images". (Formats: homebrew)
图像分析实验室
耶鲁面孔数据库 B - 5760 single light source images of 10 subjects each seen under 576 viewing conditions (9 poses x 64 illumination conditions). (Formats: PGM)
图像数据库 - An image database including some textures
JAFFE 人脸表情图像数据库 - The JAFFE database consists of 213 images of Japanese female subjects posing 6 basic facial expressions as well as a neutral pose. Ratings on emotion adjectives are also available, free of charge, for research purposes. (Formats: TIFF Grayscale images.)
ATR 研究，日本京都
JISCT 立体声评估 - 44 image pairs. These data have been used in an evaluation of stereo analysis, as described in the April 1993 ARPA Image Understanding Workshop paper ``The JISCT Stereo Evaluation'' 作者 R.C.Bolles, H.H.Baker, and M.J.Hannah, 263--274 (Formats: SSI)
与视觉纹理 - Image archive (100+ images) (Formats: ppm)
麻省理工学院面对图像等 - hundreds of images (Formats: homebrew)
机器视觉 - Images from the textbook 作者 Jain, Kasturi, Schunck (20+ images) (Formats: GIF TIFF)
乳房 X 光检查图像数据库 - 100 or more images of mammograms with ground truth. Additional images available 作者 request, and links to several other mammography databases are provided. (Formats: homebrew)
ftp://ftp.cps.msu.edu/pub/prip - many images (Formats: unknown)
Middlebury 与地面真相立体声数据集 - Six multi-frame stereo data sets of scenes containing planar regions. Each data set contains 9 color images and subpixel-accuracy ground-truth data. (Formats: ppm)
Middlebury 立体视觉研究 - Middlebury College
莫迪斯机载模拟器，图库和数据集 - High Altitude Imagery from around the world for environmental modeling in support of NASA EOS program (Formats: JPG and HDF)
NIST 指纹和手写 - datasets - thousands of images (Formats: unknown)
NIST 指纹数据 - compressed multipart uuencoded tar file
NLM HyperDoc 可视化人员项目 - Color, CAT and MRI image samples - over 30 images (Formats: jpeg)
全国设计知识库 - Over 55,000 3D CAD and solid models of (mostly) mechanical/machined engineerign designs. (Formats: gif,vrml,wrl,stp,sat)
几何与智能计算实验室
耶鲁面孔数据库 - 165 images (15 individuals) with different lighting, expression, and occlusion configurations.
OSU（MSU）三维对象模型数据库 - several sets of 3D object models collected over several years to use in object recognition research (Formats: homebrew, vrml)
OSU（MSU / WSU）数据库图像范围 - Hundreds of real and synthetic images (Formats: gif, homebrew)
OSU / SAMPL 数据库：范围图像，3D 模型，剧照，动作序列 - Over 1000 range images, 3D object models, still images and motion sequences (Formats: gif, ppm, vrml, homebrew)
信号分析和机器感知实验室
3D Vision 集团
奥塔哥光流评估序列 - Synthetic and real sequences with machine-readable ground truth optical flow fields, plus tools to generate ground truth for new sequences. (Formats: ppm,tif,homebrew)
视觉研究小组
Wiry 对象识别数据库 - Thousands of images of a cart, ladder, stool, bicycle, chairs, and cluttered scenes with ground truth labelings of edges and regions. (Formats: jpg)
ftp://ftp.limsi.fr/pub/quenot/opflow/testdata/piv/ - Real and synthetic image sequences used for testing a Particle Image Velocimetry application. These images may be used for the test of optical flow and image matching algorithms. (Formats: pgm (raw))
LIMSI-CNRS/CHM/IMM/vision
LIMSI-CNRS
光度学 3D 表面纹理数据库 - This is the first 3D texture database which provides both full real surface rotations and registered photometric stereo data (30 textures, 1680 images). (Formats: TIFF)
用于光流分析的序列（SOFA） - 9 synthetic sequences designed for testing motion analysis applications, including full ground truth of motion and camera parameters. (Formats: gif)
计算机视觉集团
视觉列表图像档案 - Many images, many formats
基于流的重建序列 - synthetic sequence for testing structure from motion algorithms (Formats: pgm)
具有真实视差和遮挡的立体图像 - a small set of synthetic images of a hallway with varying amounts of noise added. Use these images to benchmark your stereo algorithm. (Formats: raw, viff (khoros), or tiff)
斯图加特范围图像数据库 - A collection of synthetic range images taken from high-resolution polygonal models available on the web (Formats: homebrew)
部门形象理解
PRIMA, GRAVIR
AR 面数据库 - Contains over 4,000 color images corresponding to 126 people's faces (70 men and 56 women). Frontal views with variations in facial expressions, illumination, and occlusions. (Formats: RAW (RGB 24-bit))
普渡大学机器人视觉实验室
MIT-CSAIL 对象和场景数据库 - Database for testing multiclass object detection and scene recognition algorithms. Over 72,000 images with 2873 annotated frames. More than 50 annotated object classes. (Formats: jpg)
RVL SPEC-DB（特殊数据库） - A collection of over 300 real images of 100 objects taken under three different illuminaiton conditions (Diffuse/Ambient/Directed). -- Use these images to test algorithms for detecting and compensating specular highlights in color images. (Formats: TIFF )
机器人视觉实验室
查看球体数据库 - Images of 8 objects seen from many different view points. The view sphere is sampled using a geodesic with 172 images/sphere. Two sets for training and testing are available. (Formats: ppm)
Xm2vts 数据库 - The XM2VTSDB contains four digital recordings of 295 people taken over a period of four months. This database contains both image and video data of faces.
视觉，语音和信号处理中心
交通图像序列和“大理石块”序列 - thousands of frames of digitized traffic image sequences as well as the 'Marbled Block' sequence (grayscale images) (Formats: GIF)
IAKS/KOGS
Usenix 面对数据库 - Thousands of face images from many different sites (circa 994)
U Bern Face images - hundreds of images (Formats: Sun rasterfile)
U Michigan textures (Formats: compressed raw)
U Oulu wood and knots database - Includes classifications - 1000+ color images (Formats: ppm)
UCID - 一个未压缩的彩色图像数据库 - a benchmark database for image retrieval with predefined ground truth. (Formats: tiff)
机器视觉集团
UMass 视觉图像档案 - Large image database with aerial, space, stereo, medical images and more. (Formats: homebrew)
UNC 的 3D 图像数据库 - many images (Formats: GIF)
具有分割地面真实性的 USF 范围图像数据 - 80 image sets (Formats: Sun rasterimage)
奥卢大学基于物理的人脸数据库 - contains color images of faces under different illuminants and camera calibration conditions as well as skin spectral reflectance measurements of each person.
机器视觉和媒体处理单元
奥卢大学纹理数据库 - Database of 320 surface textures, each captured under three illuminants, six spatial resolutions and nine rotation angles. A set of test suites is also provided so that texture segmentation, classification, and retrieval algorithms can be tested in a standard manner. (Formats: bmp, ras, xv)

会议¶

框架¶

杂项¶

Google Plus - 深度学习社区
Caffe 网络研讨会
Github 上的 100 个 Github 资源
Word2Vec
Caffe DockerFile
TorontoDeepLEarning convnet
真棒深度学习音乐 - Curated list of articles related to deep learning scientific research applied to music
gfx.js
Torch7 备忘单
其他麻省理工学院的“高级自然语言处理”课程
其他麻省理工学院的“机器学习”课程
麻省理工学院的“学习网络：回归和分类”课程杂志
麻省理工学院的“神经编码与声音感知”课程杂志
通过 Spark 实现分布式深度学习网络
学习使用深度学习下象棋的国际象棋 AI。
复制“深入强化学习”的结果作者 DeepMind
Wiki2Vec。,从维基百科转储获取 Word2vec 矢量的实体和单词
来自 DeepMind 文章的原始代码+调整
Google deepdream - 神经网络艺术
高效，批量的 LSTM。
一个经常性的神经网络，旨在产生古典音乐。
内存网络实现 - Facebook
用 Google 的 FaceNet 深度神经网络进行人脸识别。
基本的数字识别神经网络
情感识别 API 演示 - 微软
在 TensorFlow 中加载 Caffe 模型的概念证明
YOLO：实时对象检测
AlphaGo - DeepMind 2016 年自然出版物的复制品，“通过深度神经网络和树搜索掌握 Go 的游戏”
机器学习软件工程师
机器学习很有趣！
Siraj Raval 的深度学习教程
Dockerface - Easy to install and use deep learning Faster R-CNN face detection for images and video in a docker container.

贡献¶

有什么想法，你认为是真棒，并适合在这个名单？,随意发送拉请求.