USACM Nano-Scale TTA Webinar by Prof. Gideon Simpson

Join Zoom Meeting: (https://us06web.zoom.us/j/84541274013?pwd=ZDhuM09BaUlVVlBuREhEV0sweGFlZz09: Meeting ID: 845 4127 4013/Passcode: 799065)

Date/Time: February 28; 2-3pm CST

Speaker: Gideon Simpson, Drexel University

Discussant: Petr Plechac, University of Delaware

Title: Learning dynamics with random Fourier features

A common challenge in modelling, at all scales, is how to “learn” an evolution law from time series data, allowing for prediction. Classical approaches have involved mathematical modeling with differential equations. This has been extended to the neural ODEs and PDEs, which incorporate data into fitting generalized “right hand sides” to the evolution equations with neural nets fo various architectures. Here, we make use of recently developed adaptive random Fourier feature methods to learn near optimal approximations in Fourier space, representing our evolution map, directly, in terms of trigonometric activation functions within a shallow neural network. This talk will present the method, its theoretical basis, our progress in learning dynamics, and highlight outstanding questions and future directions of activity. This is joint work with P. Plechac and J. Knap, along with graduate students. 

You do not have to register to attend.

Please forward this to anyone who may be interested.