Experimental demonstration of coupled learning in elastic networks
Lauren E. Altman, Menachem Stern, Andrea J. Liu, D. J. Durian
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.