Photonic Reservoir Computer with Output Expansion for Unsupervized Parameter Drift Compensation

Photonic Reservoir Computer with Output Expansion for Unsupervized Parameter Drift Compensation

We present a method to improve the performance of a reservoir computer by keeping the reservoir fixed and increasing the number of output neurons. The additional neurons are nonlinear functions, typically chosen randomly, of the reservoir neurons. We demonstrate the interest of this expanded output...

Full description

Bibliographic Details
Main Authors: Jaël Pauwels, Guy Van der Sande, Guy Verschaffelt, Serge Massar
Format: Article
Language:English
Published: MDPI AG 2021-07-01
Series:Entropy
Subjects:
photonic computing
reservoir computing
coherent optical reservoir
output expansion
readout weight-tuning
unsupervised noise compensation
Online Access:https://www.mdpi.com/1099-4300/23/8/955

Internet

https://www.mdpi.com/1099-4300/23/8/955

Similar Items