Bulletin of the American Physical Society
APS March Meeting 2021
Monday–Friday, March 15–19, 2021; Virtual; Time Zone: Central Daylight Time, USA
Session R01: Learning without Neurons
8:00 AM–11:00 AM,
Thursday, March 18, 2021
Sponsoring Unit: DBIO
Chair: Arvind Murugan, University of Chicago
Abstract: R01.00002 : Learning in Physical Networks: From Machine Learning to Learning Machines*
8:36 AM–9:12 AM
We show that such local learning rules can be derived for any physical network, whether in equilibrium or in steady-state. We specifically study several such systems: disordered flow networks, elastic networks, and self-folding sheets. We demonstrate how physical systems can learn to distinguish between classes in real data such as Iris flowers and handwritten digits. Finally, we discuss experimental considerations regarding the realization of learning machines in actual networks. By exploiting the advances of statistical learning theory in the real world, we propose the plausibility of new classes of smart metamaterials, adapting in-situ to users' needs.
*This research was supported in part by the National Science Foundation under Grant No. NSF PHY-1748958, and by the U.S. Department of Energy, Office of Basic Energy Sciences, Division of Materials Sciences and Engineering under Awards DE- FG02-05ER46199 and DE-SC0020963. We acknowledge NSF-MRSEC 1420709 for funding and the University of Chicago Research Computing Center for computing resources.
The American Physical Society (APS) is a non-profit membership organization working to advance the knowledge of physics.
1 Physics Ellipse, College Park, MD 20740-3844
Editorial Office 1 Research Road, Ridge, NY 11961-2701 (631) 591-4000
Office of Public Affairs 529 14th St NW, Suite 1050, Washington, D.C. 20045-2001 (202) 662-8700