View CalendarView Calendar
Lytle Lecture Series | Mathematical Mysteries of Deep Neural Networks | Stéphane Mallat
Lytle Lecture Series | Mathematical Mysteries of Deep Neural Networks  | Stéphane Mallat
WhenTuesday, Dec 3, 2019, 3:30 – 4:30 p.m.
Campus locationPaul G. Allen Center For Computer Science & Engineering (CSE)
Campus roomAtrium
Event typesAcademics, Lectures/Seminars
Event sponsorsThe Dean W. Lytle Electrical & Computer Engineering Endowed Lecture Series - Department of Electrical & Computer Engineering
Description

This lecture is free and open to the public.

World-renowned applied mathematician, Dr. Stéphane Mallat, will be the speaker for the Lytle Lecture Series on December 3, 2019. Dr. Mallat is known for his fundamental work in wavelet theory, with major impact in signal processing, music synthesis and image segmentation. He is a member of the French Academy of Sciences and the US National Academy of Engineering.

Abstract: 

Deep neural networks obtain impressive results for image, sound and language recognition or to address complex problems in physics. They are partly responsible for the renewal of artificial intelligence. Yet, we do not understand why they can work so well and why they sometimes fail, which raises many problems of robustness and explainability.

Recognizing or classifying data amounts to approximate phenomena which depend on a very large number of variables. The combinatorial explosion of possibilities makes it potentially impossible to solve. One can learn from data only if the problem is highly structured. Deep neural networks appear to take advantage of the existence of such structures, whose nature seem to be similar across a wide range of applications.  Understanding this "architecture of complexity" involves many branches of mathematics and is related to open questions in physics. I will discuss some approaches and show applications.

Linkwww.ece.uw.edu…
View CalendarView CalendarPrintPrint
Events calendar powered by Trumba