2026-07-072026-07-07http://salesiana.dossiersoluciones.com/handle/123456789/18853The 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 pagesDisordered Systems and Neural NetworksQuantitative BiologyStatistical Physics of Feedforward Neural Networkstext