Course description

Objective


Methodology
  • The course is based on a reading material set that is mainly composed of research papers and book  chapters.
  • Each paper/chapter is assigned to a session. All the students are supposed to read it. The presenter is randomly chosen.
Contents

 TopicResources Due date
Deep learning Deep Machine Learning – A New Frontier in Artificial Intelligence Research (P1)

 06/02/2012
DBN Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations, Honglak Lee, Roger Grosse, Rajesh Ranganath and Andrew Y. Ng. In Proceedings of the Twenty-Sixth International Conference on Machine Learning, 2009 (slides:pdf) (slides:ppt) (video) (paper) 20/03/2012
Deep learning Yoshua Bengio. 2009. Learning Deep Architectures for AI. Found. Trends Mach. Learn. 2, 1 (January 2009), 1-127. DOI=10.1561/2200000006 http://dx.doi.org/10.1561/2200000006 (chapters 1,2,3) (video) (slides:pdf)
 27/03/2012 
Deep learning Yoshua Bengio. 2009. Learning Deep Architectures for AI. Found. Trends Mach. Learn. 2, 1 (January 2009), 1-127. DOI=10.1561/2200000006 http://dx.doi.org/10.1561/2200000006  (chapters 4,5,6)  10/04/2012
  Bengio, Y., Lamblin, P., Popovici, D., & Larochelle, H. (2007). Greedy layer-wise training of deep networks. Advances in neural information processing systems, 19, 153. MIT;.[presentation] [pdf] - [hinton-presentation] [video-lecture] 
  Matrix Completion E. Candès and B. Recht, “Exact matrix completion via convex optimization,” Communications of the ACM, vol. 55, no. 6, p. 111, Jun. 2012. [pdf] [video] [presentation] 
 Sparse Coding[video 

Bibliography

Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations, Honglak Lee, Roger Grosse, Rajesh Ranganath and Andrew Y. Ng. In Proceedings of the Twenty-Sixth International Conference on Machine Learning, 2009