-
【推荐】深度学习各种源码实现
深度学习各种源码实现，基于Tensorflow、Theano、Torch等框架实现的一些深度学习算法源代码。
Tensorflow
(1) Neural Turing Machine(NMT).
(2) A Neural Attention Model for Abstractive Summarization
(3) Recurrent Convolutional Memory Network
(4) End-To-End Memory Networks in Tensorflow
(5) Neural Variational Inference for Text Processing---wikiQA Corpus
(6) Word2Vec
(7) CNN code for insurance QA(question Answer matching)---Insurance QA Corpus
(8) Some experiments on MovieQA with Hsieh,Tom and Huang in AMLDS
(9) Teaching Machines to Read and Comprehend
(10) Convolutional Neural Networks for Sentence Classification (kIM.EMNLP2014)Tensorflow
(11) Convolutional Neural Networks for Sentence Classification (kIM.EMNLP2014)Theano
(12) Separating Answers from Queries for Neural Reading Comprehension
(13) Neural Associative Memory for Dual-Sequence Modeling
(14) The Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systems.
Theano
(1) End-To-End Memory Networks, formerly known as Weakly Supervised Memory Networks
(2) Memory Networks
(3) Recurrent Neural Networks with External Memory for Language Understanding
(4) Attention Sum Reader model as presented in 'Text Comprehension with the Attention Sum Reader Network'--- CNN and Daily Mail news data QA
(5) character-level language models
(6) Hierarchical Encoder-Decoder
(7) A Recurrent Latent Variable Model for Sequential Data
Torch
(1) Sequence-to-sequence model with LSTM encoder/decoders and attention
(2) Chains of Reasoning over Entities, Relations, and Text using Recurrent Neural Networks
(3) Recurrent Memory Network for Language Modeling
链接：http://mp.weixin.qq.com/s?__biz=MzA4NDEyMzc2Mw==&mid=2649676197&idx=1&sn=1330c02190a3356beaf24ca1ef243574#rd
-
【推荐】Theano/Python 神经网络教程
由莫烦Python录制的Theano/Python 神经网络教程目录如下：
Theano 1 why
Theano 2 安装
Theano 3 神经网络在做什么
Theano 4 基本用法
Theano 5 function 用法
Theano 6 shared 变量
Theano 7 activation function 激励函数
Theano 8 定义 Layer 类
Theano 9 regression 回归例子
Theano 10 regression 可视化 回归例子
Theano 11 classification 分类学习
Theano 12 regularization 正则化
Theano 13 save model 保存
Theano 14 总结和更多
链接：http://mp.weixin.qq.com/s?__biz=MzA4NDEyMzc2Mw==&mid=2649676200&idx=1&sn=009b6537bc9a070eab5471529bf0c805#rd
-
【推荐】300+计算机视觉资源的终极列表
300+计算机视觉资源的终极列表，也包括一些机器学习的资源，主要包括书籍、课程、论文、数据集等，部分内容如下：
BOOKS
COMPUTER VISION
(1) Computer Vision: Models, Learning, and Inference – Simon J. D. Prince 2012
(2) Computer Vision: Theory and Application – Rick Szeliski 2010
(3) Computer Vision: A Modern Approach (2nd edition) – David Forsyth and Jean Ponce 2011
(4) Multiple View Geometry in Computer Vision – Richard Hartley and Andrew Zisserman 2004
(5) Computer Vision – Linda G. Shapiro 2001
(6) Vision Science: Photons to Phenomenology – Stephen E. Palmer 1999
(7) Visual Object Recognition synthesis lecture – Kristen Grauman and Bastian Leibe 2011
(8) Computer Vision for Visual Effects – Richard J. Radke, 2012
(9) High dynamic range imaging: acquisition, display, and image-based lighting – Reinhard, E., Heidrich, W., Debevec, P., Pattanaik, S., Ward, G., Myszkowski, K 2010
OPENCV PROGRAMMING
(1) Learning OpenCV: Computer Vision with the OpenCV Library – Gary Bradski and Adrian Kaehler
(2) Practical Python and OpenCV – Adrian Rosebrock
(3) OpenCV Essentials – Oscar Deniz Suarez, Ma del Milagro Fernandez Carrobles, Noelia Vallez Enano, Gloria Bueno Garcia, Ismael Serrano Gracia
MACHINE LEARNING
(1) Pattern Recognition and Machine Learning – Christopher M. Bishop 2007
(2) Neural Networks for Pattern Recognition – Christopher M. Bishop 1995
(3) Probabilistic Graphical Models: Principles and Techniques – Daphne Koller and Nir Friedman 2009
(4) Pattern Classification – Peter E. Hart, David G. Stork, and Richard O. Duda 2000
(5) Machine Learning – Tom M. Mitchell 1997
(6) Gaussian processes for machine learning – Carl Edward Rasmussen and Christopher K. I. Williams 2005
(7) Learning From Data– Yaser S. Abu-Mostafa, Malik Magdon-Ismail and Hsuan-Tien Lin 2012
(8) Neural Networks and Deep Learning – Michael Nielsen 2014
(9) Bayesian Reasoning and Machine Learning – David Barber, Cambridge University Press, 2012
FUNDAMENTALS
Linear Algebra and Its Applications – Gilbert Strang 1995
COURSES
COMPUTER VISION
(1) EENG 512 / CSCI 512 – Computer Vision – William Hoff (Colorado School of Mines)
(2) Visual Object and Activity Recognition – Alexei A. Efros and Trevor Darrell (UC Berkeley)
(3) Computer Vision – Steve Seitz (University of Washington)
(4) Visual Recognition – Kristen Grauman (UT Austin)
(5) Language and Vision – Tamara Berg (UNC Chapel Hill)
(6) Convolutional Neural Networks for Visual Recognition – Fei-Fei Li and Andrej Karpathy (Stanford University)
(7) Computer Vision – Rob Fergus (NYU)
(8) Computer Vision – Derek Hoiem (UIUC)
(9) Computer Vision: Foundations and Applications – Kalanit Grill-Spector and Fei-Fei Li (Stanford University)
(10) High-Level Vision: Behaviors, Neurons and Computational Models – Fei-Fei Li (Stanford University)
(11) Advances in Computer Vision – Antonio Torralba and Bill Freeman (MIT)
(12) Computer Vision – Bastian Leibe (RWTH Aachen University)
(14) Computer Vision 2 – Bastian Leibe (RWTH Aachen University)
链接：http://mp.weixin.qq.com/s?__biz=MzA4NDEyMzc2Mw==&mid=2649676196&idx=1&sn=81fecf70f4f78197c565800171ba6970#rd
-
【学习】大牛的《深度学习》笔记，60分钟带你学会Deep Learning
深度学习，即Deep Learning,是一种学习算法（Learning algorithm）,亦是人工智能领域的一个重要分支。从快速发展到实际应用，短短几年时间里，深度学习颠覆了语音识别、图像分类、文本理解等众多领域的算法设计思路，渐渐形成了一种从训练数据出发，经过一个端到端（end-to-end）的模型，然后直接输出得到最终结果的一种新模式。那么，深度学习有多深？学了究竟有几分？本文将带你领略深度学习高端范儿背后的方法与过程。
链接：http://mp.weixin.qq.com/s?__biz=MzA4NDEyMzc2Mw==&mid=2649676197&idx=4&sn=847ed0a9b8a48d5e209ccc3ef2f139da#rd
-
【推荐】自然语言处理顶级会议ACL 2016论文集下载
自然语言处理顶级会议ACL 2016论文已放出下载链接，部分论文如下：
(1) Noise reduction and targeted exploration in imitation learning for Abstract Meaning Representation parsing
(2) Data Recombination for Neural Semantic Parsing
(3) Inferring Logical Forms From Denotations
(4) Search Language to Logical Form with Neural Attention
(5) Unsupervised Person Slot Filling based on Graph Mining
(6) A Multi-media Approach to Cross-lingual Entity Knowledge Transfer
(7) Models and Inference for Prefix-Constrained Machine Translation
(8) Modeling Coverage for Neural Machine Translation
(9) Improving Neural Machine Translation Models with Monolingual Data
(10) Graph-Based Translation Via Graph Segmentation
Incremental Acquisition of Verb Hypothesis Space towards Physical World Interaction
(11) Language Transfer Learning for Supervised Lexical Substitution
(12) Learning the Curriculum with Bayesian Optimization for Task-Specific Word Representation Learning
链接：http://mp.weixin.qq.com/s?__biz=MzA4NDEyMzc2Mw==&mid=2649676199&idx=1&sn=b7030ffa4bb5f9a12b4ced162021022d#rd
-
【学习】MXNet无缝兼容Caffe Layer
链接：http://mp.weixin.qq.com/s?__biz=MzA4NDEyMzc2Mw==&mid=2649676200&idx=3&sn=d6123c4586e08c75530e9d3c5f15e68d#rd
-
【推荐】深度学习与神经网络全局概览：核心技术的发展历程
链接：http://mp.weixin.qq.com/s?__biz=MzA4NDEyMzc2Mw==&mid=2649676203&idx=1&sn=ed896fe4e302bd4f80bb73c05e6d3783#rd
-
【论文】（代码+论文）行为识别最新进展
链接：http://mp.weixin.qq.com/s?__biz=MzA4NDEyMzc2Mw==&mid=2649676200&idx=2&sn=de7532d0255e3190aa83ccd25818ba7d#rd
-
【干货】机器学习中的范数规则化之L0、L1与L2范数
链接：http://mp.weixin.qq.com/s?__biz=MzA4NDEyMzc2Mw==&mid=2649676197&idx=2&sn=b77d4b21b8b1bbe581557b4d2d6ae6db#rd
-
【学习】DL框架的未来发展，TensorFlow/MXNet/Torch, 选哪个？
链接：http://mp.weixin.qq.com/s?__biz=MzA4NDEyMzc2Mw==&mid=2649676203&idx=3&sn=4b0c28ed4ee297cfa4bd71fef69df826#rd
