Work

Optical Implementation of Equilibrium Propagation Using Spatial Photonic Ising Machines

Year: 2026

Type: preprint

Abstract: Equilibrium Propagation offers a compelling alternative to traditional machine learning for training energy-based networks. Here we demonstrate a hybrid optical-digital implementation of EP using a Spatial Photonic Ising Machine (SPIM). The SPIM exploits the gauge transformation method to optically encode both continuous neuron states and rank-1 binary trainable patterns as phase modulations via a spatial light modulator, with inference realized using a finite difference scheme. The experimental system is evaluated on the Wine classification dataset. The potential of this approach, including the use of continuous couplings and structured coupling matrices, is evaluated numerically on the more complex MNIST dataset. Our work provides a concrete pathway toward energy-efficient physical implementations of Equilibrium Propagation.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2606.13454

Authors: Abeele, Dimitri Vanden, Veraldi, Daniele, Pierangeli, Davide, Conti, Claudio, Massar, Serge

Institutions: Université Libre de Bruxelles, Sapienza University of Rome

Topic: Neural Networks and Reservoir Computing

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funders: Fonds De La Recherche Scientifique - FNRS, Fédération Wallonie-Bruxelles, Fonds Wetenschappelijk Onderzoek, Fonds pour la Formation à la Recherche dans l’Industrie et dans l’Agriculture

Award: G724384124

OpenAlex ID: W7164480046

Cites:

Cited by:

Related to: