Location: MATH 3206
Time: 1:00 PM
Day: Monday
Organizers:
Weilin Li
wl298(a)math(.)umd(.)edu
Mark Magsino
mmagsino(a)math(.)umd(.)edu




Related Seminars:

The Norbert Wiener Center Seminar

UPCOMING TALKS

Time: Tuesday, October 10, 2017, 6:30 pm @ AV Williams 2460

Speaker: Radu Balan

Title: WHEN HARMONIC ANALYSIS MEETS MACHINE LEARNING: LIPSCHITZ ANALYSIS OF DEEP CONVOLUTION NETWORKS

Abstract: Deep neural networks have led to dramatic improvements in performance for many machine learning tasks, yet the mathematical reasons for this success remain largely unclear. In this talk we present recent developments in the mathematical framework of convolutive neural networks (CNN). In particular we discuss the scattering network of Mallat and how it relates to another problem in harmonic analysis, namely the phase retrieval problem. Then we discuss the general convolutive neural network from a theoretician point of view. We present Lipschitz analysis results using two analytical methods: the chain rule (or backpropagation) and the storage function method inspired by Mallat's scattering network analysis. Towards the end of the talk we discuss how these theoretical results can be applied in practice, and in particular we mention various design methods that incorporate Lipschitz bounds as penalty terms into optimization problems.

Fall 2017/Spring 2018 Seminar Schedule
9/12 Weilin Li (UMD) abstract
9/19 Kung-Ching Lin (UMD) abstract
9/26 Prof. John Benedetto (UMD) abstract
10/3 Chenzhi Zhao (UMD) abstract
10/10 Mark Magsino (UMD) abstract
10/17 Dr. Stefano Vigogna (JHU) abstract
10/24 Prof. Robert Ghrist (Penn) abstract
10/31 Prof. Nate Strawn (Georgetown) abstract
11/7 abstract
11/14 abstract
11/21 Thanksgiving
11/28 abstract
12/5 Dr. James Murphy (JHU) abstract


* Denotes special date/time

 

Previous Years' Abstracts


University of Maryland Suite 2211, Department of Mathematics, University of Maryland, College Park, MD 20742.   Phone: (301) 405-5158,
FAX: (301) 314-0827. The Norbert Wiener Center is part of the College of Computer, Mathematical, and Natural Sciences.