BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Deep Network Representations for High Dimensional Signal Analysis
DTSTART:20140825T111500
DTSTAMP:20260407T194926Z
UID:43a78468422a09af9b9b2ac98666f009757fbd75d63dede6d3ca0afa
CATEGORIES:Conferences - Seminars
DESCRIPTION:Prof. Stéphane Mallat\, Ecole normale supérieure\, Paris\nBi
 o: Stéphane Mallat received the Ph.D. degree in electrical engineering fr
 om the University of Pennsylvania\, Philadelphia\, in 1988. In 1988\, he j
 oined the Computer Science Department of the Courant Institute of Mathemat
 ical Sciences where he was Associate Professor in 1994 and Professor in 19
 96. Since 1995\, he has been a full Professor in the Applied Mathematics D
 epartment at Ecole Polytechnique\, Paris. From 2001 to 2008 he was a co-fo
 under and CEO of a start-up company.\nProf. Mallat is an IEEE and EURASIP 
 fellow. He received the 1990 IEEE Signal Processing Society's paper award\
 , the 1993 Alfred Sloan fellowship in Mathematics\, the 1997 Outstanding A
 chievement Award from the SPIE Optical Engineering Society\, the 1997 Blai
 se Pascal Prize in applied mathematics from the French Academy of Sciences
 \, the 2004 European IST Grand prize\, the 2004 INIST-CNRS prize for most 
 cited French researcher in engineering and computer science\, and the 2007
  EADS prize of the French Academy of Sciences.\nHis research interests inc
 lude signal processing\, learning and harmonic analysis.\nRemarkable signa
 l analysis results have been obtained with deep convolution neural network
 s\, through complex and huge optimization algorithms which are difficult t
 o understand. This talks aims at better understanding these networks\, and
  show that most of it may not require any learning for structured signals 
 such as image or audio signals. Similar results are obtained a non-linear 
 filter bank algorithm\, called a scattering transform\, having the same ar
 chitecture but using predefined wavelet filters. Applications to various a
 udio and image classification problems will be shown\, as well the regress
 ion of molecule energies in quantum chemistry.
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR