Work

Latching dynamics for neural networks with a sigmoidal nonlinearity

Year: 2026

Type: article

Abstract: These notes are intended to clarify the relationship between a kind of dynamical sequential retrieving of learned states (‘latching dynamics’) which have been observed in Wilson-Cowan equations [1] with synaptic connections subjected to short term depression [2], and the same dynamics analyzed by Koksal-Ers¨ oz et al [3] on a simplified model which allows to give proofs and criteria¨ for the occurence of this behavior.

Source: Chaos Solitons & Fractals

DOI: 10.1016/j.chaos.2026.118343

Author: P. Chossat

Institutions: Centre National de la Recherche Scientifique, Institut national de recherche en sciences et technologies du numérique, Université Côte d'Azur, Laboratoire Jean-Alexandre Dieudonné

Language: English

Topic: Neural Networks and Applications

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Estimated APC paid: $3,970

Funder: Institut national de recherche en informatique et en automatique (INRIA)