Skip to Main content Skip to Navigation
Journal articles

Large deviations, dynamics and phase transitions in large stochastic heterogeneous neural networks

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.
Complete list of metadatas

https://hal.inria.fr/hal-00942206
Contributor : Jonathan Touboul <>
Submitted on : Tuesday, February 4, 2014 - 6:24:29 PM
Last modification on : Saturday, September 26, 2020 - 11:44:10 PM

Links full text

Identifiers

Citation

Tanguy Cabana, Jonathan Touboul. Large deviations, dynamics and phase transitions in large stochastic heterogeneous neural networks. Journal of Statistical Physics, Springer Verlag, 2013, 153 (2), pp.211-269. ⟨10.1007/s10955-013-0818-5⟩. ⟨hal-00942206⟩

Share

Metrics

Record views

710