View in EDS HTML Full Text PDF Full Text

Learning in Associative Networks Through Pavlovian Dynamics.

Saved in:
Bibliographic Details
Title: Learning in Associative Networks Through Pavlovian Dynamics.
Authors: Lotito, Daniele1,2 (AUTHOR) daniele.lotito@phd.unipi.it, Aquaro, Miriam3,4 (AUTHOR) miriam.aquaro@uniroma.it, Marullo, Chiara3,5 (AUTHOR) chiara.marullo@icar.cnr.it
Source: Neural Computation. Feb2025, Vol. 37 Issue 2, p311-343. 33p.
Subjects: Classical conditioning, Stochastic differential equations, Statistical equilibrium, Sleep stages, Stochastic systems
Abstract: Hebbian learning theory is rooted in Pavlov's classical conditioning While mathematical models of the former have been proposed and studied in the past decades, especially in spin glass theory, only recently has it been numerically shown that it is possible to write neural and synaptic dynamics that mirror Pavlov conditioning mechanisms and also give rise to synaptic weights that correspond to the Hebbian learning rule. In this article we show that the same dynamics can be derived with equilibrium statistical mechanics tools and basic and motivated modeling assumptions. Then we show how to study the resulting system of coupled stochastic differential equations assuming the reasonable separation of neural and synaptic timescale. In particular, we analytically demonstrate that this synaptic evolution converges to the Hebbian learning rule in various settings and compute the variance of the stochastic process. Finally, drawing from evidence on pure memory reinforcement during sleep stages, we show how the proposed model can simulate neural networks that undergo sleep-associated memory consolidation processes, thereby proving the compatibility of Pavlovian learning with dreaming mechanisms. [ABSTRACT FROM AUTHOR]
Copyright of Neural Computation is the property of MIT Press and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: egs
DbLabel: Engineering Source
An: 182438817
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Learning in Associative Networks Through Pavlovian Dynamics.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Lotito%2C+Daniele%22">Lotito, Daniele</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<i> daniele.lotito@phd.unipi.it</i><br /><searchLink fieldCode="AR" term="%22Aquaro%2C+Miriam%22">Aquaro, Miriam</searchLink><relatesTo>3,4</relatesTo> (AUTHOR)<i> miriam.aquaro@uniroma.it</i><br /><searchLink fieldCode="AR" term="%22Marullo%2C+Chiara%22">Marullo, Chiara</searchLink><relatesTo>3,5</relatesTo> (AUTHOR)<i> chiara.marullo@icar.cnr.it</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Neural+Computation%22">Neural Computation</searchLink>. Feb2025, Vol. 37 Issue 2, p311-343. 33p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Classical+conditioning%22">Classical conditioning</searchLink><br /><searchLink fieldCode="DE" term="%22Stochastic+differential+equations%22">Stochastic differential equations</searchLink><br /><searchLink fieldCode="DE" term="%22Statistical+equilibrium%22">Statistical equilibrium</searchLink><br /><searchLink fieldCode="DE" term="%22Sleep+stages%22">Sleep stages</searchLink><br /><searchLink fieldCode="DE" term="%22Stochastic+systems%22">Stochastic systems</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Hebbian learning theory is rooted in Pavlov's classical conditioning While mathematical models of the former have been proposed and studied in the past decades, especially in spin glass theory, only recently has it been numerically shown that it is possible to write neural and synaptic dynamics that mirror Pavlov conditioning mechanisms and also give rise to synaptic weights that correspond to the Hebbian learning rule. In this article we show that the same dynamics can be derived with equilibrium statistical mechanics tools and basic and motivated modeling assumptions. Then we show how to study the resulting system of coupled stochastic differential equations assuming the reasonable separation of neural and synaptic timescale. In particular, we analytically demonstrate that this synaptic evolution converges to the Hebbian learning rule in various settings and compute the variance of the stochastic process. Finally, drawing from evidence on pure memory reinforcement during sleep stages, we show how the proposed model can simulate neural networks that undergo sleep-associated memory consolidation processes, thereby proving the compatibility of Pavlovian learning with dreaming mechanisms. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Neural Computation is the property of MIT Press and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=182438817
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1162/neco_a_01730
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 33
        StartPage: 311
    Subjects:
      – SubjectFull: Classical conditioning
        Type: general
      – SubjectFull: Stochastic differential equations
        Type: general
      – SubjectFull: Statistical equilibrium
        Type: general
      – SubjectFull: Sleep stages
        Type: general
      – SubjectFull: Stochastic systems
        Type: general
    Titles:
      – TitleFull: Learning in Associative Networks Through Pavlovian Dynamics.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Lotito, Daniele
      – PersonEntity:
          Name:
            NameFull: Aquaro, Miriam
      – PersonEntity:
          Name:
            NameFull: Marullo, Chiara
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 02
              Text: Feb2025
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 08997667
          Numbering:
            – Type: volume
              Value: 37
            – Type: issue
              Value: 2
          Titles:
            – TitleFull: Neural Computation
              Type: main
ResultId 1