arXiv · 2503.03649
Limits of nonlinear and dispersive fiber propagation for an optical fiber-based extreme learning machine
Abstract
We report a generalized nonlinear Schr\"odinger 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.
Explore related subjects
Keep this discovery
Andrei V. Ermolaev, Mathilde Hary, Lev Leybov, Piotr Ryczkowski, Anas Skalli, Daniel Brunner, Goëry Genty, John M. Dudley. 2025-03-05. Limits of nonlinear and dispersive fiber propagation for an optical fiber-based extreme learning machine. https://doi.org/10.1364/ol.562186
Cite the original work for its findings. Save a collection to share your selection of sources.