Training an Ising Machine with Equilibrium Propagation

TL;DR

This paper introduces a supervised training method for Ising machines using Equilibrium Propagation, demonstrating their potential as hardware platforms for neural network training on datasets like MNIST.

Contribution

The study presents a novel supervised training approach for Ising machines with Equilibrium Propagation, enabling their application in AI tasks.

Findings

Successfully trained a neural network on MNIST using an Ising machine.

Demonstrated the feasibility of convolution operations on Ising machine connectivity.

Achieved results comparable to software-based neural network training.

Abstract

Ising machines, which are hardware implementations of the Ising model of coupled spins, have been influential in the development of unsupervised learning algorithms at the origins of Artificial Intelligence (AI). However, their application to AI has been limited due to the complexities in matching supervised training methods with Ising machine physics, even though these methods are essential for achieving high accuracy. In this study, we demonstrate a novel approach to train Ising machines in a supervised way through the Equilibrium Propagation algorithm, achieving comparable results to software-based implementations. We employ the quantum annealing procedure of the D-Wave Ising machine to train a fully-connected neural network on the MNIST dataset. Furthermore, we demonstrate that the machine's connectivity supports convolution operations, enabling the training of a compact convolutional network with minimal spins per neuron. Our findings establish Ising machines as a promising trainable hardware platform for AI, with the potential to enhance machine learning applications.