From the
FAQ of `comp.ai.neural-nets`.

Ripley, B.D. (1996) Pattern Recognition and Neural Networks, Cambridge: Cambridge University Press, ISBN 0-521-46086-7 (hardback), xii+403 pages.

Brian Ripley's new book is an excellent sequel to Bishop (1995). Ripley starts up where Bishop left off, with Bayesian inference and statistical decision theory, and then covers some of the same material on NNs as Bishop but at a higher mathematical level. Ripley also covers a variety of methods that are not discussed, or discussed only briefly, by Bishop, such as tree-based methods and belief networks. While Ripley is best appreciated by people with a background in mathematical statistics, the numerous realistic examples in his book will be of interest even to beginners in neural nets.

From Nature volume **381** page 206, (16 May 1996):

## Easy learning

Patrick Naylor

Known for his hype-free approach to neural networks, Brian Ripley here provides an excellent text on the statistics of pattern classifiers and the application of neural network techniques. With an emphasis on the statistical approach, it would have been all too easy for a book of this type to become hard work to read. Ripley has managed, however, to produce an altogether accessible text, aided by examples using both synthetic and real-world data sets. These include case studies on, believe it or not, Leptograpsus crabs and diabetes in Pima Indians.

The scope of the book is wide, and incorporates neural networks initially as methods for learning the parameters of multi-dimensional input-output relationships; only later on does Ripley make passing reference to any architectural equivalence to the brain. The opening chapter on basic decision theory and Bayes rule is substantial and leads to a development of parametric models. Other chapters cover a range of topics such as linear discriminant analysis, multilayer perceptrons and radial basis function networks, as well as unsupervised methods.

The inevitable comparison between this book and C.M. Bishop's Neural Networks for Pattern Recognition (Oxford University Press, 1995) suggests that while Bishop's book is earning a reputation for depth and rigour, Ripley's text will be rightly popular with newcomers to the area for its ability to present the mathematics of statistical pattern recognition and neural networks in an accessible format and engaging style.