Work

State Space Expansion with Nonlinear Transformation and Upsampling in Experimental Reservoir Computing

Year: 2025

Type: article

Abstract: The reservoir computing approach based on a semiconductor laser with optoelectronic time-delay feedback is distinguished by its simplicity, speed, and reliability. However, the response of the reservoir to the input signal in this configuration is a superposition of the laser relaxation oscillations, which has limited complexity, which may therefore reduce computational performance when solving problems requiring high nonlinearity. We experimentally demonstrate a combination of postprocessing techniques that overcome this limitation through upsampling and state space expansion using a nonlinear transformation of nodal functions, and show how this results in an order-of-magnitude reduction in prediction error for the Santa Fe task.

Source: Photonics

DOI: 10.3390/photonics12121236

Authors: Anton Kovalev, Evgeniy Popov, Gleb Danilenko, Vladimir Vitkin, Evgeny Viktorov

Institution: ITMO University

Language: English

Topic: Neural Networks and Reservoir Computing

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $2,896

Funders: Ministry of Science and Higher Education of the Russian Federation, Fondation Schlumberger pour l’Education et la Recherche