Conference paper Open Access

Training Convolutional Neural Networks with Competitive Hebbian Learning Approaches

Gabriele Lagani; Fabrizio Falchi; Claudio Gennaro; Giuseppe Amato


MARC21 XML Export

<?xml version='1.0' encoding='UTF-8'?>
<record xmlns="http://www.loc.gov/MARC21/slim">
  <leader>00000nam##2200000uu#4500</leader>
  <datafield tag="041" ind1=" " ind2=" ">
    <subfield code="a">eng</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Neural networks, Machine learning, Hebbian learning Competitive learning, Computer vision,Biologically inspired</subfield>
  </datafield>
  <controlfield tag="005">20220320014922.0</controlfield>
  <datafield tag="500" ind1=" " ind2=" ">
    <subfield code="a">In Nicosia G. et al. (eds) Machine Learning, Optimization, and Data Science. LOD 2021. Lecture Notes in Computer Science, vol 13163. Springer, Cham. https://doi.org/10.1007/978-3-030-95467-3_2</subfield>
  </datafield>
  <controlfield tag="001">6367135</controlfield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">CNR-ISTI</subfield>
    <subfield code="a">Fabrizio Falchi</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">CNR-ISTI</subfield>
    <subfield code="a">Claudio Gennaro</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">CNR-ISTI</subfield>
    <subfield code="a">Giuseppe Amato</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">519723</subfield>
    <subfield code="z">md5:0e518291c88a6e2eb41f885e3885ba3b</subfield>
    <subfield code="u">https://zenodo.org/record/6367135/files/ACAIN2021_paper_20.pdf</subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2022-02-02</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">openaire</subfield>
    <subfield code="p">user-ai4eu</subfield>
    <subfield code="p">user-ai4media</subfield>
    <subfield code="o">oai:zenodo.org:6367135</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">University of Pisa</subfield>
    <subfield code="a">Gabriele Lagani</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">Training Convolutional Neural Networks with Competitive Hebbian Learning Approaches</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">user-ai4eu</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">user-ai4media</subfield>
  </datafield>
  <datafield tag="536" ind1=" " ind2=" ">
    <subfield code="c">951911</subfield>
    <subfield code="a">A European Excellence Centre for Media, Society and Democracy</subfield>
  </datafield>
  <datafield tag="536" ind1=" " ind2=" ">
    <subfield code="c">825619</subfield>
    <subfield code="a">A European AI On Demand Platform and Ecosystem</subfield>
  </datafield>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="u">https://creativecommons.org/licenses/by/4.0/legalcode</subfield>
    <subfield code="a">Creative Commons Attribution 4.0 International</subfield>
  </datafield>
  <datafield tag="650" ind1="1" ind2="7">
    <subfield code="a">cc-by</subfield>
    <subfield code="2">opendefinition.org</subfield>
  </datafield>
  <datafield tag="520" ind1=" " ind2=" ">
    <subfield code="a">&lt;p&gt;We explore competitive Hebbian learning strategies to train feature detectors in Convolutional Neural Networks (CNNs), without supervision. We consider variants of the Winner-Takes-All (WTA) strategy explored in previous works, i.e. k-WTA, e-soft-WTA and p-soft-WTA, performing experiments on different object recognition datasets. Results suggest that the Hebbian approaches are effective to train early feature extraction layers, or to re-train higher layers of a pre-trained network, with soft competition generally performing better than other Hebbian approaches explored in this work. Our findings encourage a path of cooperation between neuroscience and computer science towards a deeper investigation of biologically inspired learning principles.&lt;/p&gt;</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.1007/978-3-030-95467-3_2</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">publication</subfield>
    <subfield code="b">conferencepaper</subfield>
  </datafield>
</record>
27
30
views
downloads
Views 27
Downloads 30
Data volume 15.6 MB
Unique views 21
Unique downloads 30

Share

Cite as