Limits of nonlinear and dispersive fiber propagation for an optical fiber-based extreme learning machine
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.
Authors
- Daniel Brunner (ORCID: https://orcid.org/0000-0002-4003-3056)
- Anas Skalli (ORCID: https://orcid.org/0000-0002-7039-926X)
- Mathilde Hary (ORCID: https://orcid.org/0000-0002-5338-113X)
- John M. Dudley (ORCID: https://orcid.org/0000-0001-9520-9699)
- Andrei Ermolaev (ORCID: https://orcid.org/0000-0001-6144-5124)
- Piotr Ryczkowski (ORCID: https://orcid.org/0000-0002-1837-6132)
- Goëry Genty (ORCID: https://orcid.org/0000-0002-0768-3663)
- Lev Leybov
Institutions
- Centre National de la Recherche Scientifique (FR)
- Tampere University (FI)
- Institut Universitaire de France (FR)
- Franche-Comté Électronique Mécanique Thermique et Optique - Sciences et Technologies (FR)
- Tampere University (FI)
- Université Marie et Louis Pasteur (FR)
Publication Details
- Journal
- Optics Letters
- Published
- 2025-05-30
- DOI
- https://doi.org/10.1364/ol.562186
- Citations
- 5
- Primary Topic
- Neural Networks and Reservoir Computing
- Type
- article
- Field-Weighted Citation Impact
- 12.40
Funders
- Agence Nationale de la Recherche
- Academy of Finland
- Institut Universitaire de France
- European Research Council