Asymptotic description of neural networks with correlated synaptic weights

Olivier Faugeras, James MacLaurin

Research output: Contribution to journalArticlepeer-review

7 Scopus citations

Abstract

We study the asymptotic law of a network of interacting neurons when the number of neurons becomes infinite. Given a completely connected network of neurons in which the synaptic weights are Gaussian correlated random variables, we describe the asymptotic law of the network when the number of neurons goes to infinity. We introduce the process-level empirical measure of the trajectories of the solutions to the equations of the finite network of neurons and the averaged law (with respect to the synaptic weights) of the trajectories of the solutions to the equations of the network of neurons. The main result of this article is that the image law through the empirical measure satisfies a large deviation principle with a good rate function which is shown to have a unique global minimum. Our analysis of the rate function allows us also to characterize the limit measure as the image of a stationary Gaussian measure defined on a transformed set of trajectories.

Original languageEnglish (US)
Pages (from-to)4701-4743
Number of pages43
JournalEntropy
Volume17
Issue number7
DOIs
StatePublished - 2015
Externally publishedYes

All Science Journal Classification (ASJC) codes

  • Physics and Astronomy(all)

Keywords

  • Correlated synaptic weights
  • Firing rate neurons
  • Good rate function
  • Large deviations
  • Neural networks
  • Spectral representations
  • Stationary gaussian processes
  • Stationary measures

Fingerprint Dive into the research topics of 'Asymptotic description of neural networks with correlated synaptic weights'. Together they form a unique fingerprint.

Cite this