Journal article Open Access

Continual learning for recurrent neural networks: An empirical evaluation

Andrea Cossu; Antonio Carta; Vincenzo Lomonaco; Davide Bacciu


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="URL">https://zenodo.org/record/5164245</identifier>
  <creators>
    <creator>
      <creatorName>Andrea Cossu</creatorName>
      <affiliation>University of Pisa</affiliation>
    </creator>
    <creator>
      <creatorName>Antonio Carta</creatorName>
      <affiliation>University of Pisa</affiliation>
    </creator>
    <creator>
      <creatorName>Vincenzo Lomonaco</creatorName>
      <affiliation>University of Pisa</affiliation>
    </creator>
    <creator>
      <creatorName>Davide Bacciu</creatorName>
      <affiliation>University of Pisa</affiliation>
    </creator>
  </creators>
  <titles>
    <title>Continual learning for recurrent neural networks: An empirical evaluation</title>
  </titles>
  <publisher>Zenodo</publisher>
  <publicationYear>2021</publicationYear>
  <subjects>
    <subject>continual learning; recurrent neural networks</subject>
  </subjects>
  <dates>
    <date dateType="Issued">2021-08-05</date>
  </dates>
  <language>en</language>
  <resourceType resourceTypeGeneral="JournalArticle"/>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType="url">https://zenodo.org/record/5164245</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsIdenticalTo">10.1016/j.neunet.2021.07.021</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;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;</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>
24
22
views
downloads
Views 24
Downloads 22
Data volume 34.9 MB
Unique views 22
Unique downloads 21

Share

Cite as