Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Optimizing Energy-based Neural Network Training with Coherent Ising Machine

About

While Ising machines serve as advanced physical solvers for the Ising model,enabling applications in combinatorial optimization and neural network training,their scalability for large-scale neural networks remains constrained by hardware connectivity limitations and suboptimal training methodologies. In this work,we leverage a Coherent Ising Machine (CIM) to train an energy-based neural network using Equilibrium Propagation, achieving performance comparable to existing software-based implementations. We further enhance the algorithm by integrating the Adam optimizer to solve for the ground state of a Hopfield energy network, significantly improving convergence speed and solution accuracy. Additionally, we demonstrate the scalability of our approach across deeper network architectures and convolutional operations. Our results highlight the potential of CIM dynamics as a scalable platform for training complex neural networks, offering a pathway toward energy-efficient implementations via analog circuits, optoelectronics, or integrated photonics. This work establishes a novel physical framework for next-generation AI hardware development.

Chen-Rui Fan, Bo Lu, Zhi-Hong Zhang, Run-Qing Zhang, Jing-Wei Wen, Chuan Wang• 2026

Related benchmarks

TaskDatasetResultRank
Image ClassificationMNIST (test)
Accuracy96.8
654
Classification8*8 Digits--
5
Image ClassificationMNIST Downsampled to 2x2 (digits 6, 9)--
1
Image ClassificationMNIST with low-rank interactions--
1
Showing 4 of 4 rows

Other info

Follow for update