Precision requirements for single-layer feedforward neural networks
Anne-Johan Annema, Klaas Hoen, Hans Wallinga · 2002
This paper presents a mathematical analysis of the effect of limited precision analog hardware for weight adaptation to be used in on-chip learning feedforward neural networks. Easy-to-read equations and simple worst-case estimations for the maximum tolerable imprecision are presented. As an application of the analysis, a worst-case estimation on the minimum size of the weight storage capacitors is presented.