读过的一些deep learning文章

1.      Survey

（1）      Learning Deep Architectures forAI, by Yoshua Bengio.经典中的经典，将deep learning里面各个算法的源流阐释得极为清楚。

（2）      Representation Learning: AReview and New Perspectives, by Yoshua Bengio, Aaron Courville, and PascalVincent. 内容丰富，视野开阔。同样是经典中的经典，强烈推荐。

（3）      Deep Learning Tutorial, by YannLeCun. 绝对的扛鼎之作。在这个PPT里面，LeCun展现了他作为deep learning三大牛人之一的深厚功力，对deep learning模型做了深刻全面的总结，包含大量成果介绍。

（4）      A tutor on deep learning, byKai Yu. 余凯老师的这个PPT写得深入浅出，平易近人。建议在看其他论文之前一定要认真拜读这个。

（5）      The next generation of neuralnetworks, by Geoffrey Hinton. Hinton大神的这个PPT写得清新自然，让人感觉deeplearning的出现是应运而生，有水到渠成之感。也是入门的必读之作。

（6）      Machine Learning and AI viaBrain simulations, by Andrew Ng. 也是经典的入门介绍。Andrew Ng做这个报告的视频在网上也可以找得到。

（7）     NIPS 2013 Tutorial. http://cs.nyu.edu/~fergus/pmwiki/pmwiki.php 大牛Rob Fergus在NIPS 2013上做的比较全面的tutorial

2.      RBM

（1）      A Practical Guide to TrainingRestricted Boltzmann Machines, by Geoffrey Hinton. 编程实践必读，不仅仅局限于RBM，其他deeplearning算法也可以参考。

（2）      受限波尔兹曼机简介, 张春霞等。

（3）      An Analysis of Gaussian BinaryRestricted Boltzmann Machines for Natural Images, by Nan Wang, Jan Melchior, LaurenzWiskott.

3.      Autoencoder

（1）      Autoencoders, MinimumDescription Length and Helmholtz Free Energy, by Geoffrey E. Hinton et al.

（2）      Extracting and Composing RobustFeatures with Denoising Autoencoders, by Pascal Vincent et al.

4.      CNN

（1）      Image Net Classification withDeep Convolutional Neural Networks, by Alex Krizhevsky et al.

5.      Deep Belief Networks

（1）      Deep Belief Nets, by GeoffreyHinton.

（2）      Sparse deep belief net modelfor visual area V2, by Honglak Lee et al.

（3）      Learning Convolutional FeatureHierarchies for Visual Recognition, by Koray Kavukcuoglu et al.

（4）      A Fast Learning Algorithm forDeep Belief Nets, by Geoffrey E. Hinton.

6.      Deep Boltzmann Machines

（1）      Deep Boltzmann Machines, by RuslanSalakhutdinov.

（2）      Efficient Learning of DeepBoltzmann Machines, by Ruslan Salakhutdinov et al.

（3）      Joint Training of DeepBoltzmann Machines for Classification, by Ian J. Goodfellow.

（4）      On Training Deep BoltzmannMachines, by Guillaume Desjardins et al.

（5）      A Better Way to Pretrain DeepBoltzmann Machines, by Ruslan Salakhutdinov.

（6）      An Efficient Learning Procedurefor Deep Boltzmann Machines, by Ruslan Salakhutdinov.

7.      Convolutional Deep BeliefNetworks

（1）      Convolutional Deep BeliefNetworks for Scalable Unsupervised Learning of Hierarchical Representations, byHonglak Lee et al.

（2）      Unsupervised Learning of HierarchicalRepresentations with Convolutional Deep Belief Networks, by Honglak Lee et al.

8.      Theory

（1）      Greedy Layer-Wise Training ofDeep Networks, by Yoshua Bengio et al.

（2）      On Contrastive DivergenceLearning, by Miguel A .Carreira-Perpi~n an et al.

（3）      Notes on ContrastiveDivergence, by Oliver Woodford.

9.      Resources

（1）      不错的网站：http://deeplearning.net/reading-list/

（2）      Deep Learning的软件资源：http://deeplearning.net/software_links/

（3）      一个不错的deep learning matlab工具箱：https://github.com/rasmusbergpalm/DeepLearnToolbox