Statistical Physics of Feedforward Neural Networks
Disordered Systems and Neural Networks
2007-05-23 v1 q-bio
Abstract
The article is a lightly edited version of my habilitation thesis at the University Wuerzburg. My aim is to give a self contained, if concise, introduction to the formal methods used when off-line learning in feedforward networks is analyzed by statistical physics. However, due to its origin, the article is not a comprehensive review of the field but is highly skewed towards reporting my own research.
Cite
@article{arxiv.cond-mat/0201530,
title = {Statistical Physics of Feedforward Neural Networks},
author = {Robert Urbanczik},
journal= {arXiv preprint arXiv:cond-mat/0201530},
year = {2007}
}
Comments
44 pages