Journal article Open Access

Continual learning for recurrent neural networks: An empirical evaluation

Andrea Cossu; Antonio Carta; Vincenzo Lomonaco; Davide Bacciu


DCAT Export

<?xml version='1.0' encoding='utf-8'?>
<rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:adms="http://www.w3.org/ns/adms#" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:dct="http://purl.org/dc/terms/" xmlns:dctype="http://purl.org/dc/dcmitype/" xmlns:dcat="http://www.w3.org/ns/dcat#" xmlns:duv="http://www.w3.org/ns/duv#" xmlns:foaf="http://xmlns.com/foaf/0.1/" xmlns:frapo="http://purl.org/cerif/frapo/" xmlns:geo="http://www.w3.org/2003/01/geo/wgs84_pos#" xmlns:gsp="http://www.opengis.net/ont/geosparql#" xmlns:locn="http://www.w3.org/ns/locn#" xmlns:org="http://www.w3.org/ns/org#" xmlns:owl="http://www.w3.org/2002/07/owl#" xmlns:prov="http://www.w3.org/ns/prov#" xmlns:rdfs="http://www.w3.org/2000/01/rdf-schema#" xmlns:schema="http://schema.org/" xmlns:skos="http://www.w3.org/2004/02/skos/core#" xmlns:vcard="http://www.w3.org/2006/vcard/ns#" xmlns:wdrs="http://www.w3.org/2007/05/powder-s#">
  <rdf:Description rdf:about="https://zenodo.org/record/5164245">
    <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://zenodo.org/record/5164245</dct:identifier>
    <foaf:page rdf:resource="https://zenodo.org/record/5164245"/>
    <dct:creator>
      <rdf:Description>
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>Andrea Cossu</foaf:name>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>University of Pisa</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:creator>
      <rdf:Description>
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>Antonio Carta</foaf:name>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>University of Pisa</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:creator>
      <rdf:Description>
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>Vincenzo Lomonaco</foaf:name>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>University of Pisa</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:creator>
      <rdf:Description>
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>Davide Bacciu</foaf:name>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>University of Pisa</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:title>Continual learning for recurrent neural networks: An empirical evaluation</dct:title>
    <dct:publisher>
      <foaf:Agent>
        <foaf:name>Zenodo</foaf:name>
      </foaf:Agent>
    </dct:publisher>
    <dct:issued rdf:datatype="http://www.w3.org/2001/XMLSchema#gYear">2021</dct:issued>
    <dcat:keyword>continual learning; recurrent neural networks</dcat:keyword>
    <frapo:isFundedBy rdf:resource="info:eu-repo/grantAgreement/EC/Horizon 2020 Framework Programme - Research and Innovation action/871385/"/>
    <schema:funder>
      <foaf:Organization>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">10.13039/501100000780</dct:identifier>
        <foaf:name>European Commission</foaf:name>
      </foaf:Organization>
    </schema:funder>
    <dct:issued rdf:datatype="http://www.w3.org/2001/XMLSchema#date">2021-08-05</dct:issued>
    <dct:language rdf:resource="http://publications.europa.eu/resource/authority/language/ENG"/>
    <owl:sameAs rdf:resource="https://zenodo.org/record/5164245"/>
    <adms:identifier>
      <adms:Identifier>
        <skos:notation rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://zenodo.org/record/5164245</skos:notation>
        <adms:schemeAgency>url</adms:schemeAgency>
      </adms:Identifier>
    </adms:identifier>
    <owl:sameAs rdf:resource="https://doi.org/10.1016/j.neunet.2021.07.021"/>
    <dct:isPartOf rdf:resource="https://zenodo.org/communities/teaching-h2020"/>
    <dct:description>&lt;p&gt;Learning continuously during all model lifetime is fundamental to deploy &lt;a href="https://www.sciencedirect.com/topics/computer-science/machine-learning"&gt;machine learning&lt;/a&gt; solutions robust to drifts in the data distribution. Advances in Continual Learning (CL) with &lt;a href="https://www.sciencedirect.com/topics/engineering/recurrent-neural-network"&gt;recurrent neural networks&lt;/a&gt; could pave the way to a large number of applications where incoming data is non stationary, like &lt;a href="https://www.sciencedirect.com/topics/engineering/natural-language-processing"&gt;natural language processing&lt;/a&gt; and robotics. However, the existing body of work on the topic is still fragmented, with approaches which are application-specific and whose assessment is based on heterogeneous learning protocols and datasets. In this paper, we organize the literature on CL for sequential data processing by providing a categorization of the contributions and a review of the benchmarks. We propose two new benchmarks for CL with sequential data based on existing datasets, whose characteristics resemble real-world applications.&lt;/p&gt; &lt;p&gt;We also provide a broad empirical evaluation of CL and Recurrent Neural Networks in class-incremental scenario, by testing their ability to mitigate forgetting with a number of different strategies which are not specific to sequential data processing. Our results highlight the key role played by the sequence length and the importance of a clear specification of the CL scenario.&lt;/p&gt;</dct:description>
    <dct:accessRights rdf:resource="http://publications.europa.eu/resource/authority/access-right/PUBLIC"/>
    <dct:accessRights>
      <dct:RightsStatement rdf:about="info:eu-repo/semantics/openAccess">
        <rdfs:label>Open Access</rdfs:label>
      </dct:RightsStatement>
    </dct:accessRights>
    <dct:license rdf:resource="https://creativecommons.org/licenses/by/4.0/legalcode"/>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL rdf:resource="https://doi.org/10.1016/j.neunet.2021.07.021"/>
        <dcat:byteSize>1584864</dcat:byteSize>
        <dcat:downloadURL rdf:resource="https://zenodo.org/record/5164245/files/2103.07492.pdf"/>
        <dcat:mediaType>application/pdf</dcat:mediaType>
      </dcat:Distribution>
    </dcat:distribution>
  </rdf:Description>
  <foaf:Project rdf:about="info:eu-repo/grantAgreement/EC/Horizon 2020 Framework Programme - Research and Innovation action/871385/">
    <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">871385</dct:identifier>
    <dct:title>A computing toolkit for building efficient autonomous applications leveraging humanistic intelligence</dct:title>
    <frapo:isAwardedBy>
      <foaf:Organization>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">10.13039/501100000780</dct:identifier>
        <foaf:name>European Commission</foaf:name>
      </foaf:Organization>
    </frapo:isAwardedBy>
  </foaf:Project>
</rdf:RDF>
24
22
views
downloads
Views 24
Downloads 22
Data volume 34.9 MB
Unique views 22
Unique downloads 21

Share

Cite as