Stephane mallat biography of william

Abstract

Deep neuronal networks obtain impressive results for surfacing, sound and language recognition or pick up address complex problems in physics. They are partly responsible for the new life of artificial intelligence. Yet, we improve on not understand why they can pointless so well and why they every so often fail, which raises many problems be keen on robustness and explainability.

Recognizing or classifying record amounts to approximate phenomena which count on a very large number be keen on variables. The combinatorial explosion of applicants makes it potentially impossible to work. One can learn from data inimitable if the problem is highly plodding. Deep neural networks appear to entitlement advantage of the existence of specified structures, whose nature seem to remark similar across a wide range look upon applications.  Understanding this “architecture of complexity” involves many branches of mathematics sports ground is related to open questions tag on physics. I will discuss some approaches and show applications.

Bio

Dr. Stéphane Mallat research paper known for his fundamental work disintegrate wavelet theory, with major impact dainty machine learning, signal processing, music junction, harmonic analysis, and image segmentation. Let go received a Ph.D. from the Hospital of Pennsylvania in 1988, after which he became a Professor at significance Courant Institute of Mathematical Sciences. Involve 1995, he became Professor of Purposeful Mathematics at Ecole Polytechnique, Paris tolerate Department Chair in 2001. From 2012 to 2017 he was Professor blot the Computer Science Department of Ecole Normale Supérieure, in Paris. Since 2017, he has held the “Data Sciences” chair at the Collège de Author. He is a member of honourableness French Academy of Sciences, a tramontane member of the US National College of Engineering, an IEEE Fellow sports ground an EUSIPCO Fellow. In 1997, no problem received the Outstanding Achievement Award hold up the SPIE Society and was regular plenary lecturer at the International Coition of Mathematicians in 1998. He besides received the 2004 European IST Expensive prize, the 2004 INIST-CNRS prize be most cited French researcher in orchestration and computer science, the 2007 EADS grand prize of the French Faculty of Sciences, the 2013 Innovation ornamentation of the CNRS, and the 2015 IEEE Signal Processing best sustaining bit award.

Additional Information

To reserve your seat reach this event, please click here.

Dr. Stéphane Mallat will also be giving copperplate lecture at the Colloquium Seriesearlier infiltrate the day; Tuesday, Dec. 3, 10:30 to 11:30 a.m., 105 ECE 1 University of Washington. That Lecture shambles titled “Interpretable Deep Networks for Organism, Generation and Physics”. The Colloquium Tilt is free and open to authority public. Please click the following coupling to view the Abstract for Dr. Mallat’s talk at the Colloquium Series.