Speaker: Dr. Nicole Yunger Halpern, Harvard University, ITAMP
Title: Learning About Learning By Many-Body Systems
Abstract: Far-from-equilibrium many-body systems, from soap bubbles to suspensions to polymers, learn the drives that push them. This learning has been characterized with thermodynamic properties, such as work dissipation and strain. We move beyond these macroscopic properties that were first defined for equilibrium contexts: We quantify statistical mechanical learning with machine learning. Our strategy relies on a parallel that we identify between representation learning (a machine-learning model) and statistical mechanics in the presence of a drive. We apply this parallel to measure classification ability, memory capacity, discrimination ability, and novelty detection. Numerical simulations of a spin glass illustrate our technique. This toolkit exposes self-organization that eludes detection by thermodynamic measures. Our toolkit more reliably and more precisely identifies and quantifies learning by matter.