Experimental Demonstration of Coupled Learning in Elastic 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 via iterative tuning of individual spring rest lengths. We also explore the potential of robotically controlled tunable-stiffness springs as a building block for adaptive prosthetics and manipulable actuators. These mechanical networks could feasibly be scaled to solve increasingly complex tasks, hinting at a new class of "smart" metamaterials.