Header

UZH-Logo

Maintenance Infos

Tailoring Echo State Networks for Optimal Learning


Aceituno, Pau Vilimelis; Yan, Gang; Liu, Yang-Yu (2020). Tailoring Echo State Networks for Optimal Learning. iScience, 23(9):101440.

Abstract

As one of the most important paradigms of recurrent neural networks, the echo state network (ESN) has been applied to a wide range of fields, from robotics to medicine, finance, and language processing. A key feature of the ESN paradigm is its reservoir—a directed and weighted network of neurons that projects the input time series into a high-dimensional space where linear regression or classification can be applied. By analyzing the dynamics of the reservoir we show that the ensemble of eigenvalues of the network contributes to the ESN memory capacity. Moreover, we find that adding short loops to the reservoir network can tailor ESN for specific tasks and optimize learning. We validate our findings by applying ESN to forecast both synthetic and real benchmark time series. Our results provide a simple way to design task-specific ESN and offer deep insights for other recurrent neural networks.

Abstract

As one of the most important paradigms of recurrent neural networks, the echo state network (ESN) has been applied to a wide range of fields, from robotics to medicine, finance, and language processing. A key feature of the ESN paradigm is its reservoir—a directed and weighted network of neurons that projects the input time series into a high-dimensional space where linear regression or classification can be applied. By analyzing the dynamics of the reservoir we show that the ensemble of eigenvalues of the network contributes to the ESN memory capacity. Moreover, we find that adding short loops to the reservoir network can tailor ESN for specific tasks and optimize learning. We validate our findings by applying ESN to forecast both synthetic and real benchmark time series. Our results provide a simple way to design task-specific ESN and offer deep insights for other recurrent neural networks.

Statistics

Citations

Altmetrics

Downloads

3 downloads since deposited on 16 Feb 2021
3 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Journal Article, refereed, original work
Communities & Collections:07 Faculty of Science > Institute of Neuroinformatics
Dewey Decimal Classification:570 Life sciences; biology
Scopus Subject Areas:Health Sciences > Multidisciplinary
Language:English
Date:1 September 2020
Deposited On:16 Feb 2021 09:02
Last Modified:01 Mar 2021 16:31
Publisher:Cell Press (Elsevier)
ISSN:2589-0042
OA Status:Gold
Free access at:PubMed ID. An embargo period may apply.
Publisher DOI:https://doi.org/10.1016/j.isci.2020.101440
PubMed ID:32827856

Download

Gold Open Access

Download PDF  'Tailoring Echo State Networks for Optimal Learning'.
Preview
Content: Published Version
Filetype: PDF
Size: 2MB
View at publisher
Licence: Creative Commons: Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)