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