Work

Limits of nonlinear and dispersive fiber propagation for an optical fiber-based extreme learning machine

Year: 2025

Type: article

Abstract: We report a generalized nonlinear Schrödinger equation simulation model of an extreme learning machine (ELM) based on optical fiber propagation. Using the MNIST handwritten digit dataset as a benchmark, we study how accuracy depends on propagation dynamics, as well as parameters governing spectral encoding, readout, and noise. For this dataset and with quantum noise limited input, test accuracies of over 91% and 93% are found for propagation in the anomalous and normal dispersion regimes, respectively. Our results also suggest that quantum noise on the input pulses introduces an intrinsic penalty to ELM performance.

Source: Optics Letters

DOI: 10.1364/ol.562186

Authors: Andrei V. Ermolaev, Mathilde Hary, Lev Leybov, Piotr Ryczkowski, Anas Skalli, Daniel Brunner, Goëry Genty, John M. Dudley

Institutions: Centre National de la Recherche Scientifique, Franche-Comté Électronique Mécanique Thermique et Optique - Sciences et Technologies, Université Marie et Louis Pasteur, Tampere University, University of Tampere, Institut Universitaire de France

Language: English

Topic: Neural Networks and Reservoir Computing

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funders: Agence Nationale de la Recherche, Academy of Finland, Institut Universitaire de France, European Research Council

Awards: Optimized on-demand ultrafast and broadband light sources using machine learning, G5679666954, Ingénierie et Innovation par les sciences physiques, les savoir-faire technologiques et l'interdisciplinarité, Photonics Research and Innovation, ISITE « BFC

OpenAlex ID: W4410875421

FWCI: 3.263

Cites: 23

Cited by: 8

Related to: 10