Description:

Title: Interpretable Polynomial Neural ODEs

Speaker: Linda Petzold, Computer Science and Mechanical Engineering, University of California Santa Barbara

Abstract: Neural networks have the ability to serve as universal function approximators, but they are not interpretable and do not generalize well outside of their training region. Both of these issues are problematic when trying to apply standard neural ordinary differential equations (ODEs) to dynamical systems. We introduce the polynomial neural ODE, which is a deep polynomial neural network inside of the neural ODE framework. We demonstrate the capability of polynomial neural ODEs to predict outside of the training region, as well as to perform direct symbolic regression without using additional tools such as SINDy, and explore some additional properties and challenges for Neural ODEs.

**Please note, this event will be held in person, and also online via Zoom at the following link: https://northwestern.zoom.us/j/97616676653

Special Note: This is the second of the two 2023 Reiss Lectures

-----

To subscribe to the Applied Mathematics Colloquia List send a message to LISTSERV@LISTSERV.IT.NORTHWESTERN.EDU with the command:

add esam-seminar@listserv.it.northwestern.edu youremailaddress