深度学习入门必看的书和论文？有哪些必备的技能需学习？

一些推荐文献：
1. DL非常好的科普文章，可快速浅显了解Deep Learning：http://www.nature.com/nature/journal/v521/n7553/full/nature14539.html
2. 深度学习大牛Bengio（下图右2）最近出版的一本书：Deep Learning，Deep Learning (Bengio 2015-10-03).pdf_免费高速下载
3. DL在视觉中打响的第一枪：NIPS‘12 paper：http://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf
4. Andrew Ng（右1）的tutorial: UFLDL Tutorial
5. 最后是LI Fei-Fei的Stanford University CS231n: Convolutional Neural Networks for Visual Recognition


几个必备的DL库：
1. MatConvNet
2. Caffe | Deep Learning Framework
3. Torch | Scientific computing for LuaJIT.
每种工具的网站都有对应的manual甚至是tutorial，手把手教你搭建深度网络。
******************************************************************************************************
2015-9-9 更新：
一个按照编程语言整理的深度学习库列表：Deep Learning Libraries by Language
******************************************************************************************************
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
2015-10-20 更新：
利用闲暇，收集、总结、整理了一份CNN实现细节——“Must Know Tips/Tricks in Deep Neural Networks”

作者：魏秀参
链接：http://www.zhihu.com/question/31785984/answer/55063559
来源：知乎
著作权归作者所有。商业转载请联系作者获得授权，非商业转载请注明出处。

肖凯，喜爱玩数据的人

库帅、zhen ju、李小旺 等人赞同

转自：Deep learning Reading List
Free Online Books

1. Deep Learning by Yoshua Bengio, Ian Goodfellow and Aaron Courville
2. Neural Networks and Deep Learning by Michael Nielsen
3. Deep Learning by Microsoft Research
4. Deep Learning Tutorial by LISA lab, University of Montreal

Courses

1. Machine Learning by Andrew Ng in Coursera
2. Neural Networks for Machine Learning by Geoffrey Hinton in Coursera
3. Neural networks class by Hugo Larochelle from Université de Sherbrooke
4. Deep Learning Course by CILVR lab @ NYU
5. CS231n: Convolutional Neural Networks for Visual Recognition On-Going
6. CS224d: Deep Learning for Natural Language Processing Going to start

Video and Lectures

1. How To Create A Mind By Ray Kurzweil - Is a inspiring talk
2. Deep Learning, Self-Taught Learning and Unsupervised Feature Learning By Andrew Ng
3. Recent Developments in Deep Learning By Geoff Hinton
4. The Unreasonable Effectiveness of Deep Learning by Yann LeCun
5. Deep Learning of Representations by Yoshua bengio
6. Principles of Hierarchical Temporal Memory by Jeff Hawkins
7. Machine Learning Discussion Group - Deep Learning w/ Stanford AI Lab by Adam Coates
8. Making Sense of the World with Deep Learning By Adam Coates
9. Demystifying Unsupervised Feature Learning  By Adam Coates
10. Visual Perception with Deep Learning By Yann LeCun

Papers

1. ImageNet Classification with Deep Convolutional Neural Networks
2. Using Very Deep Autoencoders for Content Based Image Retrieval
3. Learning Deep Architectures for AI
4. CMU’s list of papers

Tutorials

1. UFLDL Tutorial 1
2. UFLDL Tutorial 2
3. Deep Learning for NLP (without Magic)
4. A Deep Learning Tutorial: From Perceptrons to Deep Networks

WebSites

1. deeplearning.net
2. deeplearning.stanford.edu

Datasets

1. MNIST Handwritten digits
2. Google House Numbers from street view
3. CIFAR-10 and CIFAR-100
4. IMAGENET
5. Tiny Images 80 Million tiny images
6. Flickr Data 100 Million Yahoo dataset
7. Berkeley Segmentation Dataset 500

Frameworks

1. Caffe
2. Torch7
3. Theano
4. cuda-convnet
5. Ccv
6. NuPIC
7. DeepLearning4J

Miscellaneous

1. Google Plus - Deep Learning Community
2. Caffe Webinar
3. 100 Best Github Resources in Github for DL
4. Word2Vec
5. Caffe DockerFile
6. TorontoDeepLEarning convnet
7. Vision data sets
8. Fantastic Torch Tutorial My personal favourite. Also check out gfx.js
9. Torch7 Cheat sheet

基础的前面答案都说的挺好了，不再累述。
说点儿干货
当然，我是做RBM的。。。所以呢。。。关于模型算法的文章，我当然是推荐RBM的了。
An Introduction to Restricted Boltzmann Machines
这一篇，基础中的基础，搞明白了，RBM算是入门了。
A Practical Guide to Training Restricted Boltzmann Machines
Hinton老爷子的文章，有很多训练的技巧。
当然如果你只需要对RBM有所了解，会用，这两篇差不多了。如果想进一步研究一下。

Deep Boltzmann Machines
How to Pretrain Deep Boltzmann Machines in Two Stages
A BetterWay to Pretrain Deep Boltzmann Machines

这三篇可以对DBM有个比较初步的了解。
再想深入的话，建议把图模型好好搞一下。

作者：机器永不为奴
链接：http://www.zhihu.com/question/31785984/answer/70806178
来源：知乎
著作权归作者所有。商业转载请联系作者获得授权，非商业转载请注明出处。

推荐Stanford Lifeifei的CNN课(cs231n) + Ng的ML(cs229) + Deep Learning for NLP(cs224d)

推荐个中文入门的资料，神经网络与深度学习讲义20151211.pdf