How to Train an Oscillator Ising Machine using Equilibrium Propagation

Abstract: We show that Oscillator Ising Machines (OIMs) are prime candidates for use as neuromorphic machine learning processors with Equilibrium Propagation (EP) based on-chip learning. The inherent energy gradient descent dynamics of OIMs, combined with their standard CMOS implementation using existing fabrication processes, provide a natural substrate for EP learning. Our simulations confirm that OIMs satisfy the gradient-descending update property necessary for a scalable Equilibrium Propagation implementation and achieve 97.2(1)% test accuracy on the MNIST dataset without requiring any hardware modifications. Importantly, OIMs maintain robust performance under realistic hardware constraints, including moderate phase noise and 10-bit parameter quantization. These results establish OIMs as a promising platform for fast and energy-efficient neuromorphic computing, potentially enabling energy-based learning algorithms that have been previously constrained by computational limitations.