Trainable dynamical masking for readout-free optical computing

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bogdanov, S., Manuylovich, E., Turitsyn, S. K.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912402401918976
author Bogdanov, S.
Manuylovich, E.
Turitsyn, S. K.
author_facet Bogdanov, S.
Manuylovich, E.
Turitsyn, S. K.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_23464
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Trainable dynamical masking for readout-free optical computing
Bogdanov, S.
Manuylovich, E.
Turitsyn, S. K.
Optics
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.
title Trainable dynamical masking for readout-free optical computing
topic Optics
url https://arxiv.org/abs/2505.23464