Work

All-optical echo state network reservoir computing

Year: 2025

Type: article

Abstract: We propose an innovative design for an optical echo state network (ESN), an advanced type of reservoir computer known for its universal computational capabilities. Our design enables an optical implementation of arbitrary ESNs, featuring flexibility in optical matrix multiplication and nonlinear activation. Leveraging the nonlinear characteristics of stimulated Brillouin scattering, the architecture efficiently realizes measurement-free nonlinear activation. The approach significantly reduces computational overhead and energy consumption compared to traditional software-based methods. Comprehensive simulations validate the system's memory capacity, nonlinear processing strength, and polynomial algebra capabilities, showcasing performance comparable to software ESNs across key benchmark tasks. Our design establishes a feasible, scalable, and universally applicable framework for optical reservoir computing, suitable for diverse machine learning applications.

Source: Physical Review Research

DOI: 10.1103/3b3z-29f4

Authors: Ishwar S. Kaushik, Peter J. Ehlers, Daniel Soh

Institution: University of Arizona

Language: English

Topic: Neural Networks and Reservoir Computing

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $2,625

Funders: U.S. Department of Energy, Office of Science, Biological and Environmental Research