Saved in:
Bibliographic Details
Main Authors: Del Frate, Enrico, Shirin, Afroza, Sorrentino, Francesco
Format: Preprint
Published: 2021
Subjects:
Online Access:https://arxiv.org/abs/2108.12765
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914838397059072
author Del Frate, Enrico
Shirin, Afroza
Sorrentino, Francesco
author_facet Del Frate, Enrico
Shirin, Afroza
Sorrentino, Francesco
contents We investigate the effects of application of random time-shifts to the readouts of a reservoir computer in terms of both accuracy (training error) and performance (testing error.) For different choices of the reservoir parameters and different `tasks', we observe a substantial improvement in both accuracy and performance. We then develop a simple but effective technique to optimize the choice of the time-shifts, which we successfully test in numerical experiments.
format Preprint
id arxiv_https___arxiv_org_abs_2108_12765
institution arXiv
publishDate 2021
record_format arxiv
spellingShingle Reservoir Computers with Random and Optimized Time-Shifts
Del Frate, Enrico
Shirin, Afroza
Sorrentino, Francesco
Systems and Control
We investigate the effects of application of random time-shifts to the readouts of a reservoir computer in terms of both accuracy (training error) and performance (testing error.) For different choices of the reservoir parameters and different `tasks', we observe a substantial improvement in both accuracy and performance. We then develop a simple but effective technique to optimize the choice of the time-shifts, which we successfully test in numerical experiments.
title Reservoir Computers with Random and Optimized Time-Shifts
topic Systems and Control
url https://arxiv.org/abs/2108.12765