Satisfiability transition in asymmetric neural networks - Archive ouverte HAL Access content directly
Journal Articles Journal of Physics A: Mathematical and Theoretical Year : 2022

Satisfiability transition in asymmetric neural networks

Abstract

Asymmetry in the synaptic interactions between neurons plays a crucial role in determining the memory storage and retrieval properties of recurrent neural networks. In this work, we analyze the problem of storing random memories in a network of neurons connected by a synaptic matrix with a definite degree of asymmetry. We study the corresponding satisfiability and clustering transitions in the space of solutions of the constraint satisfaction problem associated with finding synaptic matrices given the memories. We find, besides the usual SAT/UNSAT transition at a critical number of memories to store in the network, an additional transition for very asymmetric matrices, where the competing constraints (definite asymmetry vs. memories storage) induce enough frustration in the problem to make it impossible to solve. This finding is particularly striking in the case of a single memory to store, where no quenched disorder is present in the system.
Fichier principal
Vignette du fichier
2204.03577.pdf (998.57 Ko) Télécharger le fichier
Origin Publisher files allowed on an open archive

Dates and versions

hal-03721474 , version 1 (08-04-2024)

Identifiers

Cite

Fabián Aguirre-López, Mauro Pastore, Silvio Franz. Satisfiability transition in asymmetric neural networks. Journal of Physics A: Mathematical and Theoretical, 2022, ⟨10.1088/1751-8121/ac79e5⟩. ⟨hal-03721474⟩
15 View
6 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More