Literature DB >> 33611064

Fading memory echo state networks are universal.

Lukas Gonon1, Juan-Pablo Ortega2.   

Abstract

Echo state networks (ESNs) have been recently proved to be universal approximants for input/output systems with respect to various Lp-type criteria. When 1≤p<∞, only p-integrability hypotheses need to be imposed, while in the case p=∞ a uniform boundedness hypotheses on the inputs is required. This note shows that, in the last case, a universal family of ESNs can be constructed that contains exclusively elements that have the echo state and the fading memory properties. This conclusion could not be drawn with the results and methods available so far in the literature.
Copyright © 2021 The Authors. Published by Elsevier Ltd.. All rights reserved.

Keywords:  Echo state network; Echo state property; Fading memory property; Machine learning; Reservoir computing; Universality

Mesh:

Year:  2021        PMID: 33611064     DOI: 10.1016/j.neunet.2021.01.025

Source DB:  PubMed          Journal:  Neural Netw        ISSN: 0893-6080


  1 in total

1.  Towards Embedded Computation with Building Materials.

Authors:  Dawid Przyczyna; Maciej Suchecki; Andrew Adamatzky; Konrad Szaciłowski
Journal:  Materials (Basel)       Date:  2021-03-31       Impact factor: 3.623

  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.