Harnessing intuitive local evolution rules for physical learning

TL;DR

This paper presents BEASTAL, a novel physical learning scheme that enables systems to learn tasks using local rules with minimal power, only controlling boundary parameters, advancing physical implementations of machine learning.

Contribution

Introduces BEASTAL, a boundary-controlled physical learning scheme using local rules, capable of linear and non-linear task learning without large memory or complex internal structures.

Findings

BEASTAL successfully performs regression and classification tasks.

The scheme achieves optimal performance with non-linear local evolution rules.

It advances physical learning by reducing complexity and power consumption.

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.