主要是顺着Bengio的PAMI review的文章找出来的。包括几本综述文章，将近100篇论文，各位山头们的Presentation。全部都可以在google上找到。
BTW：由于我对视觉尤其是检测识别比较感兴趣，所以关于DL的应用主要都是跟Vision相关的。在其他方面比如语音或者NLP，很少或者几乎没有。个人非常看好CNN和Sparse Autoencoder，这个list也反映了我的偏好，仅供参考。
Review Book List:
[2009 Thesis] Learning Deep Generative Models.pdf
[2009] Learning Deep Architectures for AI.pdf
[2013 DengLi Review] Deep Learning for Signal and Information Processing.pdf
http://deeplearning.net/tutorial/deeplearning.pdf
Paper List:
[1996 Nature] sparse coding.pdf
[1997 Vision] Sparse coding with an overcomplete basis set.pdf
[1998 NIPS] EM Algorithms for PCA and SPCA.pdf
[1998 PIEEE] Gradient-Based Learning Applied to Document Recognition.pdf
[1999] Probabilistic Principal Component Analysis.pdf
[2002 NC] Training Products of Experts by Minimizing Contrastive Divergence.pdf
[2005 JMLR] Estimation of non-normalized statistical models by score matching.pdf
[2006 NC] A fast learning algorithm for deep belief nets.pdf
[2006 NIPS] Efficient Learning of Sparse Representations with an Energy-Based Model.pdf
[2006 NIPS] Efficient sparse coding algorithms.pdf
[2006 Science] Neural Network Dimension Reduction.pdf
[2006] A Tutorial on Energy-Based Learning.pdf
[2006] To Recognize Shapes, First Learn to Generate Images montrealTR.pdf
[2007 BOOK] Scaling Learning Algorithms towards AI.pdf
[2007 CVPR] Unsupervised Learning of Invariant Feature Hierarchies with Applications to Object Recognition.pdf
[2007 ICML] Self-taught learning transfer learning from unlabeled data.pdf
[2007 NIPS TR] Greedy Layer-Wise Training of Deep Networks.pdf
[2007 NIPS] Sparse deep belief net model for visual area V2.pdf
[2007 NIPS] Sparse Feature Learning for Deep Belief Networks.pdf
[2007] Energy-Based Models in Document Recognition and Computer Vision.pdf
[2008 ICML] Extracting and Composing Robust Features with Denoising Autoencoders.pdf
[2008 ICML] Training restricted Boltzmann machines using approximations to the likelihood gradient.pdf
[2008 PSD] Fast Inference in Sparse Coding Algorithms with Applications to Object Recognition.pdf
[2009 AISTATS] Deep Boltzmann Machines.pdf
[2009 CVPR] Learning invariant features through topographic filter maps.pdf
[2009 CVPR] Linear Spatial Pyramid Matching Using Sparse Coding for Image Classification.pdf
[2009 ICCV] What is the Best Multi-Stage Architecture for Object Recognition.pdf
[2009 ICML] Using Fast Weights to Improve Persistent Contrastive Divergence.pdf
[2009 JMLR] Exploring Strategies for Training Deep Neural Networks.pdf
[2009 NIPS] Nonlinear Learning using Local Coordinate Coding.pdf
[2010 AISTATS] Efficient Learning of Deep Boltzmann Machines.pdf
[2010 AISTATS] On the convergence properties of contrastive divergence.pdf
[2010 CVPR] Learning Mid-Level Features For Recognition.pdf
[2010 CVPR] Locality-constrained Linear Coding for Image Classification.pdf
[2010 CVPR] Modeling Pixel Means and Covariances Using Factorized Third-Order Boltzmann Machines.pdf
[2010 ECCV] Image classification using super-vector coding of local image descriptors.pdf
[2010 ICML] A Theoretical Analysis of Feature Pooling in Visual Recognition.pdf
[2010 ICML] Deep learning via Hessian-free optimization.pdf
[2010 ICML] Learning Deep Boltzmann Machines using Adaptive MCMC.pdf
[2010 ISCAS] Convolutional Networks and Applications in Vision.pdf
[2010 JMLR] Stacked Denoising Autoencoders Learning Useful Representations.pdf
[2010 JMLR] Why Does Unsupervised Pre-training Help Deep Learning.pdf
[2010 NIPS] Learning Convolutional Feature Hierarchies for Visual Recognition.pdf
[2010 NIPS] Regularized estimation of image statistics by Score Matching.pdf
[2011 CACM] Unsupervised Learning of Hierarchical Representations with Convolutional Deep Belief Networks.pdf
[2011 CVPR] Learning image representations from the pixel level via hierarchical sparse coding.pdf
[2011 ICCV] Adaptive Deconvolutional Networks for Mid and High Level Feature Learning.pdf
[2011 ICML] Contractive Auto-Encoders.pdf
[2011 ICML] Learning Deep Energy Models.pdf
[2011 ICML] On Autoencoders and Score Matching for Energy Based Models.pdf
[2011 ICML] On optimization methods for deep learning.pdf
[2011 ICML] Unsupervised Models of Images by Spike-and-Slab RBMs.pdf
[2011 JMLR] Unsupervised and transfer learning challenge a deep learning approach.pdf
[2011 NC] A Connection Between Score Matching and Denoising Autoencoders.pdf
[2011 NIPS] Algorithms for Hyper-Parameter Optimization.pdf
[2011 NIPS] Spike-and-Slab Sparse Coding for Unsupervised Feature Discovery.pdf
[2011 UAI] Asymptotic efficiency of deterministic estimators for discrete energy-based models Ratio matching and pseudolikelihood.pdf
[2011] On the Expressive Power of Deep Architectures.pdf
[2012 Book] A Practical Guide to Training Restricted Boltzmann Machines.pdf
[2012 Dropout] Improving neural networks by preventing co-adaptation of feature detectors.pdf
[2012 ICML] A Generative Process for Sampling Contractive Auto-Encoders.pdf
[2012 ICML] Building High-level Features Using Large Scale Unsupervised Learning.pdf
[2012 ICML] Large-Scale Feature Learning With Spike-and-Slab Sparse Coding.pdf
[2012 JMLR] Random Search for Hyper-Parameter Optimization.pdf
[2012 NC] An Efficient Learning Procedure for Deep Boltzmann Machines.pdf
[2012 NIPS] A Better Way to Pre-Train Deep Boltzmann Machines.pdf
[2012 NIPS] Discriminative Learning of Sum-Product Networks.pdf
[2012 NIPS] ImageNet Classification with Deep Convolutional Neural Networks.pdf
[2012 NIPS] Practical Bayesian Optimization of Machine Learning Algorithms.pdf
[2012] Deep Learning via Semi-Supervised Embedding.pdf
[2013 BOOK] Deep Learning of Representations.pdf
[2013 ICLR] Stochastic Pooling for Regularization of Deep Convolutional Neural Networks.pdf
[2013 ICLR] What Regularized Auto-Encoders Learn from the Data Generating Distribution.pdf
[2013 ICML] Better Mixing via Deep Representations.pdf
[2013 ICML] No more pesky learning rates.pdf
[2013 ICML] On autoencoder scoring.pdf
[2013 ICML] On the importance of initialization and momentum in deep learning.pdf
[2014 ICML] Regularization of Neural Networks using DropConnect.pdf
[2013 NIPS] Adaptive dropout for training deep neural networks.pdf
[2013 NIPS] Deep Fisher Networks for Large-Scale Image Classification.pdf
[2013 NIPS] Deep Neural Networks for Object Detection.pdf
[2013 NIPS] Dropout Training as Adaptive Regularization.pdf
[2013 NIPS] Generalized Denoising Auto-Encoders as Generative Models.pdf
[2013 NIPS] Learning a Deep Compact Image Representation for Visual Tracking.pdf
[2013 NIPS] Learning Multi-level Sparse Representations.pdf
[2013 NIPS] Understanding Dropout.pdf
[2013 PAMI] Deep Hierarchies in the Primate Visual Cortex What Can We Learn For Computer Vision.pdf
[2013 PAMI] Deep Learning with Hierarchical Convolutional Factor Analysis.pdf
[2013 PAMI] Invariant Scattering Convolution Networks.pdf
[2013 PAMI] Learning Hierarchical Features for Scene Labeling.pdf
[2013 PAMI] Learning with Hierarchical-Deep Models.pdf
[2013 PAMI] Representation Learning A Review and New Perspectives.pdf
[2013 PAMI] Scaling Up Spike-and-Slab Models for Unsupervised Feature Learning.pdf
[2013 TR] Maxout networks.pdf
[2013 TR] Practical recommendations for gradient-based training of deep architectures.pdf
[2013] Network in Network.pdf
[2013] Visualizing and Understanding Convolutional Networks.pdf
Presentation List:
2007 Deep Belief Nets by hinton on nips2007.pdf
2009 Learning Deep Architectures by Yoshua Bengio.pdf
2010 Tutorial on Deep Learning and Applications by Honglak Lee on nips2010 workshop.pdf
2010 Unsupervised Learning by ranzato on nips2010 workshop.pdf
2012 A Tutorial on Deep Learning by yukai.pdf
2012 Deep Learning Methods for Vision on cvpr2012.pdf
2013 Deep Learning for Computer Vision by Rob Fergus on icml2013.pdf
2013 Deep Learning for Vision Tricks of the Trade by ranzato on bavm2013.pdf
2013 Deep Learning of Representations by Yoshua Bengio on aaai2013.pdf
2013 Deep Learning of Representations by Yoshua Bengio on sstic2013.pdf
2013 Deep Learning Tutorial by lecun && ranzato on icml2013.pdf
2013 Large-Scale Visual Recognition With Deep Learning by ranzato on cvpr2013.pdf
2013 Recent Advances in Deep Learning by Kevin Duh.pdf
2013 Recent Developments in Deep Neural Networks by hinton on icassp2013.pdf
DeepLearning_SummerSchool\2012 Advanced Hierarchical Models by Salakhutdinov on ipam2012.pdf
DeepLearning_SummerSchool\2012 An Algebraic Perspective on Deep Learning on ipam2012.pdf
DeepLearning_SummerSchool\2012 An Informal Mathematical Tour of Feature Learning on ipam2012.pdf
DeepLearning_SummerSchool\2012 Deep Gated MRF's on ipam2012.pdf
DeepLearning_SummerSchool\2012 Deep Learning & Feature Learning Methods for Vision on ipam2012.pdf
DeepLearning_SummerSchool\2012 Deep learning in the visual cortex on ipam2012.pdf
DeepLearning_SummerSchool\2012 Deep Learning Tutorial by hinton on ipam2012.pdf
DeepLearning_SummerSchool\2012 Deep Learning, Graphical Models, EnergyBased Models, Structured Prediction by LeCun on ipam2012.pdf
DeepLearning_SummerSchool\2012 From natural scene statistics to models of neural coding and representation on ipam2012.pdf
DeepLearning_SummerSchool\2012 Introduction to MCMC for Deep Learning on ipam 2012.pdf
DeepLearning_SummerSchool\2012 Large-Scale Deep Learning on ipam2012.pdf
DeepLearning_SummerSchool\2012 Learning Hierarchical Generative Models on ipam2012.pdf
DeepLearning_SummerSchool\2012 Learning Hierarchies of Invariant Features by LeCun on ipam 2012.pdf
DeepLearning_SummerSchool\2012 Machine Learning and AI via Brain simulations by Andrew Ng on ipam2012.pdf
DeepLearning_SummerSchool\2012 Multiview Feature Learning on ipam2012.pdf
DeepLearning_SummerSchool\2012 Neural Networks Representation Non-linear hypotheses on ipam2012.pdf
DeepLearning_SummerSchool\2012 Scattering Invariant Deep Networks for Classification by Mallat on ipam2012.pdf
zz from http://blog.sciencenet.cn/blog-520608-751519.html
other references
