Regular graphs maximize the variability of random neural networks.
Phys Rev E Stat Nonlin Soft Matter Phys
; 92(3): 032802, 2015 Sep.
Article
em En
| MEDLINE
| ID: mdl-26465523
ABSTRACT
In this work we study the dynamics of systems composed of numerous interacting elements interconnected through a random weighted directed graph, such as models of random neural networks. We develop an original theoretical approach based on a combination of a classical mean-field theory originally developed in the context of dynamical spin-glass models, and the heterogeneous mean-field theory developed to study epidemic propagation on graphs. Our main result is that, surprisingly, increasing the variance of the in-degree distribution does not result in a more variable dynamical behavior, but on the contrary that the most variable behaviors are obtained in the regular graph setting. We further study how the dynamical complexity of the attractors is influenced by the statistical properties of the in-degree distribution.
Texto completo:
1
Base de dados:
MEDLINE
Assunto principal:
Redes Neurais de Computação
Tipo de estudo:
Clinical_trials
/
Prognostic_studies
Idioma:
En
Revista:
Phys Rev E Stat Nonlin Soft Matter Phys
Assunto da revista:
BIOFISICA
/
FISIOLOGIA
Ano de publicação:
2015
Tipo de documento:
Article
País de afiliação:
França