Experimental Demonstration of Coupled Learning in Elastic Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Altman, Lauren E., Stern, Menachem, Liu, Andrea J., Durian, Douglas J.
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913420066947072
author Altman, Lauren E.
Stern, Menachem
Liu, Andrea J.
Durian, Douglas J.
author_facet Altman, Lauren E.
Stern, Menachem
Liu, Andrea J.
Durian, Douglas J.
contents Coupled learning is a contrastive scheme for tuning the properties of individual elements within a network in order 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 demonstrate a proof-of-concept mechanical network that can learn simple tasks such as self-symmetrizing 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.
format Preprint
id arxiv_https___arxiv_org_abs_2311_00170
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Experimental Demonstration of Coupled Learning in Elastic Networks
Altman, Lauren E.
Stern, Menachem
Liu, Andrea J.
Durian, Douglas J.
Soft Condensed Matter
Disordered Systems and Neural Networks
Coupled learning is a contrastive scheme for tuning the properties of individual elements within a network in order 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 demonstrate a proof-of-concept mechanical network that can learn simple tasks such as self-symmetrizing 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.
title Experimental Demonstration of Coupled Learning in Elastic Networks
topic Soft Condensed Matter
Disordered Systems and Neural Networks
url https://arxiv.org/abs/2311.00170