arXiv:2401.10955 Abstract | arXiv Analytics

arXiv:2401.10955 [math.PR]Abstract References Reviews Resources

Replica Mean Field limits for neural networks with excitatory and inhibitory activity

Published 2024-01-19Version 1

We study Replica Mean Field limits for a neural system of infinitely many neurons with both inhibitory and excitatory interactions. As a result we obtain an analytical characterisation of the invariant state. In particular we focus on the Galves-L\"ocherbach model with interactions beyond the Uniform Summability Principle.

Comments: arXiv admin note: substantial text overlap with arXiv:1907.09012

Categories: math.PR

Keywords: neural networks, inhibitory activity, study replica mean field limits, uniform summability principle, neural system

Related articles: Most relevant | Search more

arXiv:1311.4400 [math.PR] (Published 2013-11-18, updated 2013-12-13)

Asymptotic description of neural networks with correlated synaptic weights

Olivier Faugeras, James MacLaurin

arXiv:1905.07769 [math.PR] (Published 2019-05-19)

Mean-Field Langevin Dynamics and Energy Landscape of Neural Networks

Kaitong Hu, Zhenjie Ren, David Siska, Lukasz Szpruch

arXiv:math/0405343 [math.PR] (Published 2004-05-18)

Empirical margin distributions and bounding the generalization error of combined classifiers