Theoryofthebackpropagationneuralnetwork-Neural.PDF

Theory of the Backpropagation Neural Network Robert Hecht-Nielsen HNC, Inc. 5501 Oberlin Drive San Diego, CA 92121 619-546-8877 and Department of Electrical and Computer Engineering University of Caliiomia at San Diego La Jolla, CA 92139 Abstract Backpropagationis currently the most widely applied neural network architecture. Tbe informationprocessing operation that it carries out is the approximation of a mapping or function f :A C R -R, from a bounded subset A of n-dimensional Euclidean space to a bonnded subset AA] of m-dimensional Euclidean space, by means of training on examples (XI,yl), (XZ, y ~ ). ., .,(Xt. yt), . ..of the mappings action, where yk = f ( X k ) . It is assumed that such examples are generated by selecting XI vectors randomly from A in accordance with a fixed probability density function Ax). This paper presents a survey of the basic theory of the backpropagation neural network architecture covering the areas of: architectnral design, performance measurement, function approximation capability. and learning. The survey includes previously known material, as well as some new results: a formulation of the backpropagation neural network architecture to make it a valid neural network (past formnlationsviolated