This textbook provides the first comprehensivetreatment of feed-forward networks from the perspective of statisticalpattern recognition. After introducing the basic concepts of pattern recognition, the book describes techniques for modelling probability densityfunctions, and discusses the properties and relative merits of the multi-layerperceptron and radial basis function network models. It also motivates the useof various forms of error function, and reviews the principal algorithms forerror function minimization. There is a detailed discussion of learning and generalization inneural networks, and the important topics of data processing, featureextraction, and prior knowledge are also covered. The book concludes with an extensivetreatment of Bayesian techniques and their applications to neural networks.