Contrastive power-efficient physical learning in resistor networks

Menachem Stern, Sam Dillavou, Dinesh Jayaraman, Douglas Durian, Andrea Liu

Keywords: Coupled Learning, Contrastive learning, Neuromorphic computing, Power efficiency, Resistor networks

TL;DR: We show in theory and lab experiments how physical learning machines can be trained to find low power learning solutions.

Abstract: The prospect of substantial reductions in the power consumption of AI is a major motivation for the development of neuromorphic hardware. Less attention has been given to the complementary research of power-efficient learning rules for such systems. Here we study self-learning physical systems trained by local learning rules based on contrastive learning. We show how the physical learning rule can be biased toward finding power-efficient solutions to learning problems, and demonstrate in simulations and laboratory experiments the emergence of a trade-off between power-efficiency and task performance.

Submission Number: 2