Conference paper Open Access

Continual Learning with Echo State Networks

Andrea Cossu; Davide Bacciu; Antonio Carta; Claudio Gallicchio; Vincenzo Lomonaco


DataCite XML Export

<?xml version='1.0' encoding='utf-8'?>
<resource xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://datacite.org/schema/kernel-4" xsi:schemaLocation="http://datacite.org/schema/kernel-4 http://schema.datacite.org/meta/kernel-4.1/metadata.xsd">
  <identifier identifierType="DOI">10.5281/zenodo.5164243</identifier>
  <creators>
    <creator>
      <creatorName>Andrea Cossu</creatorName>
      <affiliation>University of Pisa</affiliation>
    </creator>
    <creator>
      <creatorName>Davide Bacciu</creatorName>
      <affiliation>University of Pisa</affiliation>
    </creator>
    <creator>
      <creatorName>Antonio Carta</creatorName>
      <affiliation>University of Pisa</affiliation>
    </creator>
    <creator>
      <creatorName>Claudio Gallicchio</creatorName>
      <affiliation>University of Pisa</affiliation>
    </creator>
    <creator>
      <creatorName>Vincenzo Lomonaco</creatorName>
      <affiliation>University of Pisa</affiliation>
    </creator>
  </creators>
  <titles>
    <title>Continual Learning with Echo State Networks</title>
  </titles>
  <publisher>Zenodo</publisher>
  <publicationYear>2021</publicationYear>
  <subjects>
    <subject>continual learning; echo state networks; recurrent neural networks</subject>
  </subjects>
  <dates>
    <date dateType="Issued">2021-08-05</date>
  </dates>
  <language>en</language>
  <resourceType resourceTypeGeneral="ConferencePaper"/>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType="url">https://zenodo.org/record/5164243</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsVersionOf">10.5281/zenodo.5164242</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="URL" relationType="IsPartOf">https://zenodo.org/communities/teaching-h2020</relatedIdentifier>
  </relatedIdentifiers>
  <rightsList>
    <rights rightsURI="https://creativecommons.org/licenses/by/4.0/legalcode">Creative Commons Attribution 4.0 International</rights>
    <rights rightsURI="info:eu-repo/semantics/openAccess">Open Access</rights>
  </rightsList>
  <descriptions>
    <description descriptionType="Abstract">&lt;p&gt;Continual Learning (CL) refers to a learning setup where&lt;br&gt;
data is non stationary and the model has to learn without forgetting ex-&lt;br&gt;
isting knowledge. The study of CL for sequential patterns revolves around&lt;br&gt;
trained recurrent networks. In this work, instead, we introduce CL in the&lt;br&gt;
context of Echo State Networks (ESNs), where the recurrent component&lt;br&gt;
is kept fixed. We provide the first evaluation of catastrophic forgetting in&lt;br&gt;
ESNs and we highlight the benefits in using CL strategies which are not&lt;br&gt;
applicable to trained recurrent models. Our results confirm the ESN as a&lt;br&gt;
promising model for CL and open to its use in streaming scenarios.&lt;/p&gt;</description>
  </descriptions>
  <fundingReferences>
    <fundingReference>
      <funderName>European Commission</funderName>
      <funderIdentifier funderIdentifierType="Crossref Funder ID">10.13039/501100000780</funderIdentifier>
      <awardNumber awardURI="info:eu-repo/grantAgreement/EC/Horizon 2020 Framework Programme - Research and Innovation action/871385/">871385</awardNumber>
      <awardTitle>A computing toolkit for building efficient autonomous applications leveraging humanistic intelligence</awardTitle>
    </fundingReference>
  </fundingReferences>
</resource>
23
16
views
downloads
All versions This version
Views 2323
Downloads 1616
Data volume 2.0 MB2.0 MB
Unique views 2020
Unique downloads 1515

Share

Cite as