CSAIL Event Calendar
Deep Architectures and Deep Learning: Theory, Algorithms, and Applications.
Speaker: Pierre Baldi, University of California, Irvine
Date: Thursday, December 13 2012
Time: 3:30PM to 4:30PM
Location: Patil/ Kiva Seminar Room 32-G449
Host: Tomaso Poggio, Lorenzo Rosasco, Laboratory for Computational and Statistical Learn
Contact: Kathleen Sullivan, 617-253-0551, email@example.comRelevant URL: http://lcsl.mit.edu/cml-seminars.html
Abstract: Deep architectures are important for machine learning, for engineering applications, and for understanding the brain. In this talk, we will provide a brief historical overview of deep architectures from their 1950s origins to today. Motivated by this overview, we will study and prove several theorems regarding deep architectures and one of their main ingredients--autoencoder circuits--in particular in the unrestricted Boolean and unrestricted probabilistic cases. We will show how these analyses lead to a new family of learning algorithms for deep architectures--the deep target (DT) algorithms. The DT approach converts the problem of learning a deep architecture into the problem of learning many shallow architectures by providing learning targets for each deep layer. Finally, we will present simulation results and applications of deep architectures and DT algorithms to the protein structure prediction problem.