paper

Statistical Physics of Feedforward Neural Networks

arXiv:cond-mat/0201530

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.

44 pages

Statistical Physics of Feedforward Neural Networks · wovepaper