Harnessing intuitive local evolution rules for physical learning
This work addresses the need for energy-efficient machine learning implementations, offering a novel approach for physical learning systems, though it appears incremental by building on previous schemes.
The paper tackles the problem of high computational and power costs in machine learning by introducing a training scheme for physical systems that minimizes power dissipation using only boundary control, achieving autonomous learning for regression and classification tasks with performance optimized when local rules are non-linear.
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.