ECE Colloquium - October 30, 2013
Dr. Peter Ramadge, Princeton University
CoRE Building Lecture Hall
The sparse representation of signals with respect to an over-complete dictionary has been of recent interest in a broad range of applications. One of the most used methods for obtaining sparse codes, the Lasso problem, becomes computationally costly for large dictionaries and this hinders the use of this approach for large-scale decision tasks. Recently, dictionary screening has been used to address this computational issue.
In this spirit, this talk shows how sequential Lasso screening can also facilitate faster completion of sparse representation decision tasks, such as classification, without a major impact on statistical accuracy. The sequential screening process allows us to employ an early decision mechanism that can accelerate classification, possibly at the cost of small decrease in accuracy. The talk will discuss the theoretical background that underlies these methods and demonstrate results on several classification tasks. In particular, for clip-level music genre classification, using scattering features and a new voting scheme, we show that the proposed method yields improved clip classification accuracy and considerable computational speedup.
Dr. Peter Ramadge received the B.Sc. and B.E. degrees and the M.E. degree from the University of Newcastle, Australia, and the Ph.D. degree from the Department of Electrical Engineering at the University of Toronto, Canada. He joined the faculty of Princeton University in September 1984, where he is currently Gordon Y.S. Wu Professor of Engineering, and Professor of Electrical Engineering.
Dr. Ramadge has been a visiting Professor at the Massachusetts Institute of Technology and a Visiting Research Scientist at IBM's Tokyo Research Laboratory. He is a Fellow of the IEEE and a member of SIAM. He has received several honors and awards including: a paper selected for inclusion in IEEE book "Control Theory: Twenty Five Seminal Papers (1932-1981)", an Outstanding Paper Award from the Control Systems Society of the IEEE and is listed in ISIHighlyCited.com. His current research is in the domain of statistical signal processing and machine learning, and fMRI data analysis.