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

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.

arXiv comment18 pages, 9 figures

References in corpus (13)

• A high-bias, low-variance introduction to Machine Learning for physicists
• Designing allostery-inspired response in mechanical networks
• Global Optimization, Local Adaptation, and the Role of Growth in Distribution Networks
• Directed aging, memory and Nature's greed
• A Theory of Local Learning, the Learning Channel, and the Optimality of Backpropagation
• The limits of multifunctionality in tunable networks
• Supervised learning in a mechanical system
• Periodic training of creeping solids
• Shaping dynamical folding and misfolding pathways in mechanical metamaterials
• Effect of aging on the non-linear elasticity and memory formation in materials
• Conformational Control of Mechanical Networks
• Revealing structure-function relationships in functional flow networks via persistent homology
• Tuning and jamming reduced to their minima

Cited by in corpus (19)

• Demonstration of Decentralized, Physics-Driven Learning
• Desynchronous Learning in a Physics-Driven Learning Network
• Self-learning Machines based on Hamiltonian Echo Backpropagation
• Local rules for fabricating allosteric networks
• The Physical Effects of Learning
• Learning to self-fold at a bifurcation
• Beyond backpropagation: bilevel optimization through implicit differentiation and equilibrium propagation
• Training Coupled Phase Oscillators as a Neuromorphic Platform using Equilibrium Propagation
• Rigidity of Epithelial Tissues as a Double Optimization Problem
• Physical networks become what they learn
• Memory capacity of adaptive flow networks
• A universal approximation theorem for nonlinear resistive networks
• Bilevel optimization in flow networks: A message-passing approach
• More is less in unpercolated active solids
• Noise-based Local Learning using Stochastic Magnetic Tunnel Junctions
• Profusion of Transition Pathways for Interacting Hysterons
• Harnessing intuitive local evolution rules for physical learning
• Physical learning beyond the quasistatic limit
• From Active to Odd to Smart Matter