Skip to Main content Skip to Navigation
New interface
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 metadata

https://hal.inria.fr/hal-00942206
Contributor : Jonathan Touboul Connect in order to contact the contributor
Submitted on : Tuesday, February 4, 2014 - 6:24:29 PM
Last modification on : Thursday, March 17, 2022 - 10:08:43 AM

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, 2013, 153 (2), pp.211-269. ⟨10.1007/s10955-013-0818-5⟩. ⟨hal-00942206⟩

Share

Metrics

Record views

330