Year: 2024
Type: article
Abstract: Coupled learning is a contrastive local learning scheme for tuning the properties of individual elements within a network to achieve desired functionality of the system. It takes advantage of physics both to learn using local rules and to ``compute'' the output response to input data, thus enabling the system to perform decentralized computation without the need for a processor or external memory. We present three proof-of-concept mechanical networks of increasing complexity, and demonstrate how they can learn tasks such as self-symmetrization and node allostery via iterative tuning of individual spring rest lengths. These mechanical networks could feasibly be scaled and automated to solve increasingly complex tasks, hinting at a new class of smart metamaterials.
Source: Physical Review Applied
Institution: University of Pennsylvania
Language: English
Subfield: Mechanical Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: green
Funders: National Science Foundation, U.S. Department of Energy, Simons Foundation, Aspen Center for Physics, Flatiron Health, Materials Research Science and Engineering Center, Harvard University, Engineering and Physical Sciences Research Council, Division of Materials Research, Division of Mathematical Sciences, Basic Energy Sciences, Division of Materials Sciences and Engineering
Awards: G1051554911, G155958390, Materials Research Science and Engineering Center, G2352061593, G2567800894, G2595738051, G3261929919, G342638498, Materials Research Science and Engineering Centers (MRSEC) UPENN, BIO-MIMETIC MATERIAL DESIGN BASED ON PRINCIPLES OF DISORDER, G6176141556, G638484911, G7110120067, G7391687344, G7775912750, Programs on Critical Problems in Physics, Astrophysics and Biophysics at the Aspen Center for Physics
OpenAlex ID: W4401981478