Regular graphs maximize the variability of random neural networks
arXiv:1402.3555 · doi:10.1103/PhysRevE.92.032802
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.
References in corpus (9)
- Statistical physics of social dynamics
- Topological and Dynamical Complexity of Random Neural Networks
- Extensive load in multitasking associative networks
- From Dyson to Hopfield: Processing on hierarchical networks
- Heterogeneous connections induce oscillations in large scale networks
- Large deviations, dynamics and phase transitions in large stochastic heterogeneous neural networks
- Excitable elements controlled by noise and network structure
- Heterogeneous Mean Field for neural networks with short term plasticity
- Optimal system size for complex dynamics in random neural networks near criticality