Recently I engaged in studying Deep Learning, which was motivated by G. E. Hinton from University of Toronto in 2006. The striking paper
1. G. E. Hinton,et al..Reducing the dimensionality of data with neural networks. Nature,2006.
2. G. E. Hinton,et al..A Fast Learning Algorithm for Deep Belief Nets. Neural Computaion,2006.
3. Marc' Aurelio Ranzato, Yann LeCun. Efficient Learning of Sparse Representations with an
4. Yoshua Bengio. Greedy Layer-Wise Training of Deep Networks.ICML,2007.
5. Jason Weston. Deep Learning via Semi-supervised Embedding. ICML,2008.
6. Yoshua Bengio. Learning Deep Architectures for AI. Foundations and Trends in Machine Learning,2009. (Review)
7. Hugo Larochelle,Yoshua Bengio. Exploring Strategies for Training Deep Neural Networks. Journal of Machine Learning Research,2009.
8. Dumitru Erhan,Yoshua Bengio. The Difficulty of Training Deep Architectures and the Effect of Unsupervised Pre-Training. ICML,2009.
9. Pascal Vincent,Yohusa Bengio. Stacked Denoising Autoencoders- Learning Useful Representations in a Deep Network with a Local Denoising Criterion. Journal of Machine Learning Research,2010.
10. Itamar Arel. Deep Machine Learning: A New Friontier in Artificial Interlligence Research. IEEE Computation Intelligence Magazine,2010.
11. Dumitru Erhan,Yoshua Bengio. Why Does Unsupervised Pre-training Help Deep Learning. Journal of Machine Learning Research,2010.
12. Xavier Glorot,Yoshua Bengio. Understanding the difficulty of training deep feedforward neural networks. AISTATS,2010.