On Friday, March 26th, MATRIX is pleased to host Dr. Matthew Hirn of Michigan State University as part of our seminar series. More information about Dr. Hirn’s research may be found on his webpage.  All spring seminars will be hosted via Zoom. Full details regarding the seminar may be found below –

Understanding convolutional neural networks through signal processing

Dr. Matthew Hirn

Department of Computational Mathematics, Science and Engineering; Department of Mathematics

Michigan State University

Friday, March 26, 2021

11 AM -12 PM CST

tinyurl.com/MATRIXSpringSeminar

Abstract: Convolutional neural networks (CNNs) are the go-to tool for signal processing tasks in machine learning. But how and why do they work so well? Using the basic guiding principles of CNNs, namely their convolutional structure, invariance properties, and multi-scale nature, we will discuss how the CNN architecture arises as a natural bi-product of these principles using the language of nonlinear signal processing. In doing so we will extract some core ideas that allow us to apply these types of algorithms in various contexts, including the multi-reference alignment inverse problem, generative models for textures, and supervised machine learning for quantum many particle systems. Time permitting, we will also discuss how these core ideas can be used to generalize CNNs to manifolds and graphs, while still being able to provide mathematical guarantees on the nature of the representation provided by these tools.