Hello everyone,

I want to let you know that the first Statistics and Data Science seminar of the semester is on Monday, January 29, 10:20am. 

This time our speaker is Harbir Antil and he will be talking about algorithm design using DNN. For more details see below this message.

Notice that this talk will be online. Please, join via zoom using this link
https://tennessee.zoom.us/j/97051653635

Best,
Ioannis



Title: Algorithm Design and Approximation Using DNNs

Speaker: Harbir Antil, George Mason University

Abstract: This talk begins by addressing the question whether DNNs can be used to generate algorithms and not just function approximations. This is explored with the help of an example where a DNN architecture is shown to be the exact equivalent of explicit Runge-Kutta time integrator. Remarkably, the weights and biases are given, i.e., no training is needed. The second part of the talk focuses on designing efficient DNN architectures to approximate solutions to parameterized PDEs and inverse problems. Efficiency arise by introducing nonlocality and by reducing the DNN parameter search space. With the help of various examples in fluid dynamics, wave equations, and complex flows, the efficiency of these networks is illustrated without sacrificing the accuracy. 




—
Ioannis Sgouralis, Ph.D.

Assistant Professor
Department of Mathematics
University of Tennessee, Knoxville
e-mail: [log in to unmask]
web: https://www.math.utk.edu/info/labs/sgouralis
zoom: tennessee.zoom.us/my/sgouralis
twitter: @SgouralResearch


=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-

To leave the list go here:
https://listserv.utk.edu/cgi-bin/wa?SUBED1=MATHTALK&A=1