Large deviations, dynamics and phase transitions in large stochastic heterogeneous neural networks
arXiv:1302.6951 · doi:10.1007/s10955-013-0818-5
Abstract
We analyze the macroscopic behavior of multi-populations randomly connected neural networks with interaction delays. Similar to cases occurring in spin glasses, we show that the sequences of empirical measures satisfy a large deviation principle, and converge towards a self-consistent non-Markovian process. The proof differs in that we are working in infinite-dimensional spaces (interaction delays), non-centered interactions and multiple cell types. The limit equation is qualitatively analyzed, and we identify a number of phase transitions in such systems upon changes in delays, connectivity patterns and dispersion, particularly focusing on the emergence of non-equilibrium states involving synchronized oscillations.
References in corpus (7)
- Stimulus-Dependent Suppression of Chaos in Recurrent Neural Networks
- A constructive mean field analysis of multi population neural networks with random synaptic weights and stochastic inputs
- Topological and Dynamical Complexity of Random Neural Networks
- Noise-induced behaviors in neural mean field dynamics
- Propagation of chaos in neural fields
- Heterogeneous connections induce oscillations in large scale networks
- Mean-field equations for stochastic firing-rate neural fields with delays: Derivation and noise-induced transitions
Cited by in corpus (14)
- Power-law statistics and universal scaling in the absence of criticality
- Transition to chaos in random neuronal networks
- Transition to chaos in random networks with cell-type-specific connectivity
- Optimal sequence memory in driven random networks
- Interacting diffusions on random graphs with diverging degrees: hydrodynamics and large deviations
- Dynamical Theory for Adaptive Systems
- Irreversibility in Non-reciprocal Chaotic Systems
- A local Echo State Property through the largest Lyapunov exponent
- Regular graphs maximize the variability of random neural networks
- Context-dependent representation in recurrent neural networks
- Hierarchy of chaotic dynamics in random modular networks
- Stationary-State Statistics of a Binary Neural Network Model with Quenched Disorder
- Universality of the mean-field equations of networks of Hopfield-like neurons
- Symmetries constrain dynamics in a family of balanced neural networks