Skip to main content

Organized by the University of Chicago’s Eric and Wendy Schmidt AI in Science Postdoctoral Fellowship Program.

Agenda
4:30pm – 5:15pm: Presentation
5:15pm – 5:30pm: Q&A
5:30pm – 6:00pm: Reception

Meeting location
William Eckhardt Research Center. Room 401
5640 S Ellis Avenue, Chicago, IL 60637
Map It

Abstract: Symmetry can occur in many forms. For physical systems in 3D, we have the freedom to choose any coordinate system and therefore any physical property must transform predictably under elements of Euclidean symmetry (3D rotations, translations and inversion). For algorithms involving the nodes and edges of graphs, we have symmetry under permutation of how the nodes and edges are ordered in computer memory.  Unless coded otherwise, machine learned models make no assumptions about the symmetry of a problem and will be sensitive to e.g. an arbitrary choice of coordinate system or ordering of nodes and edges in an array.

In this talk, I will break down the variety of methods used in machine learning to overcome this from data-augmentation to canonicalization to symmetry-based methods. I hope to give an intuitive overview for the types of mathematical concepts and operations that arise in these methods, present recent advances in this area, and show applications of these methods in science and engineering. I will also discuss properties of the various approaches in terms of smoothness of representation, data-efficiency, and generalization.

Bio: Tess Smidt is an Assistant Professor of Electrical Engineering and Computer Science at MIT. Tess earned her SB in Physics from MIT in 2012 and her PhD in Physics from the University of California, Berkeley in 2018. Her research focuses on machine learning that incorporates physical and geometric constraints, with applications to materials design. Prior to joining the MIT EECS faculty, she was the 2018 Alvarez Postdoctoral Fellow in Computing Sciences at Lawrence Berkeley National Laboratory and a Software Engineering Intern on the Google Accelerated Sciences team where she developed Euclidean symmetry equivariant neural networks which naturally handle 3D geometry and geometric tensor data.


Parking
Campus North Parking
5505 S Ellis Ave
Map It

arrow-left-smallarrow-right-large-greyarrow-right-large-yellowarrow-right-largearrow-right-long-yellowarrow-right-smallclosefacet-arrow-down-whitefacet-arrow-downCheckedCheckedlink-outmag-glass