Next Article in Journal
Model Selection for Non-Negative Tensor Factorization with Minimum Description Length
Previous Article in Journal
Spherical Fuzzy Logarithmic Aggregation Operators Based on Entropy and Their Application in Decision Support Systems
Previous Article in Special Issue
Stability Analysis for Memristor-Based Complex-Valued Neural Networks with Time Delays
Article Menu

Export Article

Open AccessArticle

Stationary-State Statistics of a Binary Neural Network Model with Quenched Disorder

Laboratory of Neural Computation, Center for Neuroscience and Cognitive [email protected], Istituto Italiano di Tecnologia, 38068 Rovereto, Italy
*
Author to whom correspondence should be addressed.
Entropy 2019, 21(7), 630; https://doi.org/10.3390/e21070630
Received: 20 May 2019 / Revised: 17 June 2019 / Accepted: 23 June 2019 / Published: 26 June 2019
(This article belongs to the Special Issue Statistical Mechanics of Neural Networks)
  |  
PDF [1733 KB, uploaded 3 July 2019]
  |  

Abstract

In this paper, we study the statistical properties of the stationary firing-rate states of a neural network model with quenched disorder. The model has arbitrary size, discrete-time evolution equations and binary firing rates, while the topology and the strength of the synaptic connections are randomly generated from known, generally arbitrary, probability distributions. We derived semi-analytical expressions of the occurrence probability of the stationary states and the mean multistability diagram of the model, in terms of the distribution of the synaptic connections and of the external stimuli to the network. Our calculations rely on the probability distribution of the bifurcation points of the stationary states with respect to the external stimuli, calculated in terms of the permanent of special matrices using extreme value theory. While our semi-analytical expressions are exact for any size of the network and for any distribution of the synaptic connections, we focus our study on networks made of several populations, that we term “statistically homogeneous” to indicate that the probability distribution of their connections depends only on the pre- and post-synaptic population indexes, and not on the individual synaptic pair indexes. In this specific case, we calculated analytically the permanent, obtaining a compact formula that outperforms of several orders of magnitude the Balasubramanian-Bax-Franklin-Glynn algorithm. To conclude, by applying the Fisher-Tippett-Gnedenko theorem, we derived asymptotic expressions of the stationary-state statistics of multi-population networks in the large-network-size limit, in terms of the Gumbel (double exponential) distribution. We also provide a Python implementation of our formulas and some examples of the results generated by the code. View Full-Text
Keywords: stationary states; multistability; binary neural networks; quenched disorder; bifurcations; extreme value theory; order statistics; matrix permanent; Fisher-Tippett-Gnedenko theorem; Gumbel distribution stationary states; multistability; binary neural networks; quenched disorder; bifurcations; extreme value theory; order statistics; matrix permanent; Fisher-Tippett-Gnedenko theorem; Gumbel distribution
Figures

Figure 1

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).

Supplementary material

SciFeed

Share & Cite This Article

MDPI and ACS Style

Fasoli, D.; Panzeri, S. Stationary-State Statistics of a Binary Neural Network Model with Quenched Disorder. Entropy 2019, 21, 630.

Show more citation formats Show less citations formats

Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Related Articles

Article Metrics

Article Access Statistics

1

Comments

[Return to top]
Entropy EISSN 1099-4300 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top