Trainable dynamical masking for readout-free optical computing
Optics
2025-05-30 v1
Abstract
Nonlinear systems, transforming an input signal into a high-dimensional output feature space, can be used for non-conventional computing. This approach, however, requires a change of system parameters during training rather than coefficients in a software program. We propose here to use available off-the-shelf high-speed optical communication devices and technologies to implement a trainable dynamical mask in addition to or even instead of the traditional readout layer for extreme learning machine-based computing. The computational potential of the proposed approach is demonstrated with both regression and time series prediction tasks.
Cite
@article{arxiv.2505.23464,
title = {Trainable dynamical masking for readout-free optical computing},
author = {S. Bogdanov and E. Manuylovich and S. K. Turitsyn},
journal= {arXiv preprint arXiv:2505.23464},
year = {2025}
}