Topological and Dynamical Complexity of Random Neural Networks

Abstract : Random neural networks are dynamical descriptions of randomly interconnected neural units. These show a phase transition to chaos as a disorder parameter is increased. The microscopic mechanisms underlying this phase transition are unknown, and similarly to spin-glasses, shall be fundamentally related to the behavior of the system. In this Letter we investigate the explosion of complexity arising near that phase transition. We show that the mean number of equilibria undergoes a sharp transition from one equilibrium to a very large number scaling exponentially with the dimension on the system. Near criticality, we compute the exponential rate of divergence, called topological complexity. Strikingly, we show that it behaves exactly as the maximal Lyapunov exponent, a classical measure of dynamical complexity. This relationship unravels a microscopic mechanism leading to chaos which we further demonstrate on a simpler class of disordered systems, suggesting a deep and underexplored link between topological and dynamical complexity.
Type de document :
Article dans une revue
Physical Review Letters, American Physical Society, 2013, 110, pp.118101
Liste complète des métadonnées

https://hal.inria.fr/hal-00942212
Contributeur : Jonathan Touboul <>
Soumis le : mardi 4 février 2014 - 18:29:42
Dernière modification le : dimanche 9 décembre 2018 - 01:26:05

Lien texte intégral

Identifiants

  • HAL Id : hal-00942212, version 1
  • ARXIV : 1210.5082

Citation

Gilles Wainrib, Jonathan Touboul. Topological and Dynamical Complexity of Random Neural Networks. Physical Review Letters, American Physical Society, 2013, 110, pp.118101. 〈hal-00942212〉

Partager

Métriques

Consultations de la notice

663