Joint Colloquium Distinguished Lecture Series

Image Classification with Invariant Representations

stephane mallat

Wednesday, April 6, 2011
306 Soda Hall (HP Auditorium)
4:00 - 5:00 pm

Stéphane Mallat
Professor, Ecole Polytechnique, Paris, France

Downloadable pdf


Classification requires finding appropriate metrics to compare signals. Audio and visual perceptual metrics remain a mystery. They are invariant to particular groups of transformations such as translations and scaling and are continuous to deformations relatively to these group actions. Such invariant representations can linearize classification problems, but finding them is a challenge.


Stéphane Mallat is a Professor in the Computer Science Department of the Courant Institute of Mathematical Sciences at New York University, and a Professor in the Applied Mathematics Department at Ecole Polytechnique, Paris, France. He has been a visiting professor in the ElectricalEngineering Department at Massachusetts Institute of Technology and in the Applied Mathematics Department at the University of Tel Aviv. Dr. Mallat received the 1990 IEEE Signal Processing Society's paper award, the 1993 Alfred Sloan fellowship in Mathematics, the 1997Outstanding Achievement Award from the SPIE Optical Engineering Society, and the 1997 Blaise Pascal Prize in applied mathematics, from theFrench Academy of Sciences.

  Return to EECS Joint Colloquium