Supervised learning in physical networks: From machine learning to learning machines

TL;DR

This paper introduces physical coupled learning, enabling materials and networks to adapt to forces and develop desired functions through local, plausible learning rules, paving the way for smart, adaptive metamaterials.

Contribution

It develops local learning rules applicable to any physical network, facilitating in-situ adaptation without prior design for specific tasks.

Findings

Derived local learning rules for equilibrium and steady-state networks

Demonstrated adaptability in disordered flow and elastic networks

Proposed new classes of smart, self-adapting metamaterials

Abstract

Materials and machines are often designed with particular goals in mind, so that they exhibit desired responses to given forces or constraints. Here we explore an alternative approach, namely physical coupled learning. In this paradigm, the system is not initially designed to accomplish a task, but physically adapts to applied forces to develop the ability to perform the task. Crucially, we require coupled learning to be facilitated by physically plausible learning rules, meaning that learning requires only local responses and no explicit information about the desired functionality. We show that such local learning rules can be derived for any physical network, whether in equilibrium or in steady state, with specific focus on two particular systems, namely disordered flow networks and elastic networks. By applying and adapting advances of statistical learning theory to the physical world, we demonstrate the plausibility of new classes of smart metamaterials capable of adapting to users' needs in-situ.