3 papers
cs.ET2026
Power law scaling for classification accuracy in physical neural networks
Andrei V. Ermolaev, Mathilde Hary, Anas Skalli +7
Physical neural networks (PNNs) harness the intrinsic complexity of physical systems to perform neural computation, potentially at speeds and energy efficiencies inaccessible to co…
physics.optics2025
Limits of nonlinear and dispersive fiber propagation for an optical fiber-based extreme learning machine
Andrei V. Ermolaev, Mathilde Hary, Lev Leybov +5
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 d…
nlin.PS2024
Automating physical intuition in nonlinear fiber optics with unsupervised dominant balance search
Andrei V. Ermolaev, Christophe Finot, Goery Genty +1
Identifying the underlying processes that locally dominate physical interactions is the key to understanding nonlinear dynamics. Machine-learning techniques have recently been show…