This book provides the first comprehensive treatment of feed-forward neural networks from the perspective of statistical pattern recognition After introducing the basic concepts of pattern recognition the book describes techniques for modelling probability density functions & discusses the properties & relative merits of the multi-layer perceptron & radial basis function network models It also motivates the use of various forms of error functions & reviews the principal algorithms for error function minimization As well as providing a detailed discussion of learning & generalization in neural networks the book also covers the important topics of data processing feature extraction & prior knowledge The book concludes with an extensive treatment of Bayesian techniques & their applications to neural networks