Neural Networks for Pattern Recognition - Grand Format

In this textbook, Chris Bishop provides the first comprehensive treatment of feed-forward networks from the perspective of statistical pattern recognition. After introducing the basic concepts of pattern recognition, he describes techniques for modelling probability density functions, and discusses the properties and relative merits of the multi-layer perceptron and radial basis function network models.
He also motivates the use of various forms of error function, and reviews the principal algorithms for error function minimization. There is a detailed discussion of learning and generalization in neural networks, and the important topics of data processing, feature extraction, and prior knowledge are also covered. He concludes with an extensive treatment of Bayesian techniques and their applications to neural networks.