English

Finite Size Effects in Separable Recurrent Neural Networks

Disordered Systems and Neural Networks 2009-10-31 v1

Abstract

We perform a systematic analytical study of finite size effects in separable recurrent neural network models with sequential dynamics, away from saturation. We find two types of finite size effects: thermal fluctuations, and disorder-induced `frozen' corrections to the mean-field laws. The finite size effects are described by equations that correspond to a time-dependent Ornstein-Uhlenbeck process. We show how the theory can be used to understand and quantify various finite size phenomena in recurrent neural networks, with and without detailed balance.

Keywords

Cite

@article{arxiv.cond-mat/9803386,
  title  = {Finite Size Effects in Separable Recurrent Neural Networks},
  author = {A. Castellanos and A. C. C. Coolen and L. Viana},
  journal= {arXiv preprint arXiv:cond-mat/9803386},
  year   = {2009}
}

Comments

24 pages LaTex, with 4 postscript figures included

R2 v1 2026-07-22T12:03:04.388Z