EUVIMEDEUVIMED entdecken
Crossref

From Pavlov Conditioning to Hebb Learning

Elena Agliari, Miriam Aquaro, Adriano Barra, Alberto Fachechi, Chiara Marullo

Neural Computation · 18.04.2023 · 35 (5) · 930-957

DOI: 10.1162/neco_a_01578 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Neural Computation, online erschienen am 18.04.2023. Verfasst von Elena Agliari und 4 weiteren Autor:innen. Beteiligte Einrichtung: Sapienza University of Rome, Department of Mathematics, 00185, Rome, Italy. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 35 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Hebb's learning traces its origin in Pavlov's classical conditioning; however, while the former has been extensively modeled in the past decades (e.g., by the Hopfield model and countless variations on theme), as for the latter, modeling has remained largely unaddressed so far. Furthermore, a mathematical bridge connecting these two pillars is totally lacking. The main difficulty toward this goal lies in the intrinsically different scales of the information involved: Pavlov's theory is about correlations between concepts that are (dynamically) stored in the synaptic matrix as exemplified by the celebrated experiment starring a dog and a ringing bell; conversely, Hebb's theory is about correlations between pairs of neurons as summarized by the famous statement that neurons that fire together wire together. In this letter, we rely on stochastic process theory to prove that as long as we keep neurons' and synapses' timescales largely split, Pavlov's mechanism spontaneously takes place and ultimately gives rise to synaptic weights that recover the Hebbian kernel.

Autor:innen und Institutionen

  • Sapienza University of Rome, Department of Mathematics, 00185, Rome, Italy.
  • Istituto Nazionale d'Alta Matematica, 00185, Rome, Italy elena.agliari@uniroma1.it.
  • Istituto Nazionale d'Alta Matematica, 00185, Rome, Italy miriam.aquaro@uniroma1.it.
  • Istituto Nazionale d'Alta Matematica, 00185, Rome, Italy.
  • University of Salento, Lecce 73100, Italy adriano.barra@unisalento.it.
  • Istituto Nazionale d'Alta Matematica, 00185, Rome, Italy alberto.fachechi@uniroma1.it.

Zitieren

APA

Agliari, E., Aquaro, M., Barra, A., Fachechi, A., & Marullo, C. (2023). From Pavlov Conditioning to Hebb Learning. Neural Computation, 35(5), 930-957. https://doi.org/10.1162/neco_a_01578

Vancouver

Agliari E, Aquaro M, Barra A, Fachechi A, Marullo C. From Pavlov Conditioning to Hebb Learning. Neural Computation. 2023;35(5):930-957. doi:10.1162/neco_a_01578

BibTeX
@article{Agliari2023,
  author = {Agliari, Elena and Aquaro, Miriam and Barra, Adriano and Fachechi, Alberto and Marullo, Chiara},
  title = {From Pavlov Conditioning to Hebb Learning},
  journal = {Neural Computation},
  year = {2023},
  volume = {35},
  number = {5},
  pages = {930--957},
  doi = {10.1162/neco_a_01578}
}
Kostenlos starten →