Harnessing intuitive local evolution rules for physical learning

Abstract

Machine Learning, however popular and accessible, is computationally intensive and highly power-consuming, prompting interest in alternative physical implementations of learning tasks. We introduce a training scheme for physical systems that minimize power dissipation in which only boundary parameters (i.e. inputs and outputs) are externally controlled. Using this scheme, these Boundary-Enabled Adaptive State Tuning Systems (BEASTS) learn by exploiting local physical rules. Our scheme, BEASTAL (BEAST-Adaline), is the closest analog of the Adaline algorithm for such systems. We demonstrate this autonomous learning in silico for regression and classification tasks. Our approach advances previous physical learning schemes by using intuitive, local evolution rules without requiring large-scale memory or complex internal architectures. BEASTAL can perform any linear task, achieving best performance when the local evolution rule is non-linear.

26 pages, 6 figures (with appendices). Submitted to Physical Review E

References in corpus (16)

• Deep physical neural networks enabled by a backpropagation algorithm for arbitrary physical systems
• Designing allostery-inspired response in mechanical networks
• Explaining Neural Scaling Laws
• Learning without neurons in physical systems
• One-step regression and classification with crosspoint resistive memory arrays
• Directed aging, memory and Nature's greed
• Demonstration of Decentralized, Physics-Driven Learning
• The limits of multifunctionality in tunable networks
• Supervised learning in physical networks: From machine learning to learning machines
• Rapid fair sampling of XY spin Hamiltonian with a laser simulator
• Effect of aging on the non-linear elasticity and memory formation in materials
• Self-learning Machines based on Hamiltonian Echo Backpropagation
• Learned multi-stability in mechanical networks
• The Physical Effects of Learning
• Learning to self-fold at a bifurcation
• Drive-specific adaptation in disordered mechanical networks of bistable springs