Classification by Invariant Scattering
Speaker: Dr. Stephane Mallat , Applied Mathematics, Ecole Polytechnique, Paris
Date: September 10 2010
Time: 2:00PM to 3:00PM
Location: Singleton Auditorium, MIT 46-3002
Host: Prof. Tomaso A. Poggio, CBCL, McGovern Inst., BCS Dept. & CSAIL
Contact: Kathleen D. Sullivan, 617-253-0551, kdsulliv@mit.edu
Relevant URL: http://cbcl.mit.edu/Abstract: Signal classes are usually invariant to groups of operators such as
translations or scalings, and to larger Lie groups of deformations. Classification thus requires finding informative invariants. Invariants are also at the core of quantum physics through Gauge theories. We introduce non-linear invariant operators, similar to quantum scattering. These operators
have small commutators with elastic deformations and provide new representations of stationary processes. Their computational architecture reminds deep neural networks, but learning is needed at a single layer, and implemented with O(N) operations. State of the art results are shown for image classification of deformed patterns and random textures.
See other events that are part of Brains and Machines Seminar Series 2010/2011
See other events happening in September 2010
