2025/05/04 by Gower, Alex · 1 citation
Computer Science · Physics and Astronomy · #Disordered Systems and Neural Networks (cond-mat.dis-nn) #Evolutionary Algorithms and Applications #FOS: Physical sciences #Quantum Computing Algorithms and Architecture #Quantum many-body systems
paper · pdf · doi:10.48550/arxiv.2505.02103
openalex publication_date 2025/05/04 · openalex created_date 2025/10/16 · openalex updated_date 2026/07/28
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±0.1% test accuracy on MNIST and ∼ 88.0±0.1% on Fashion-MNIST without requiring any significant hardware modifications. Importantly, OIMs maintain robust performance under realistic hardware constraints, including 10-bit parameter quantization, 4-bit phase measurement precision, and moderate phase noise that can potentially be beneficial with parameter optimization. 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.