This is the first comprehensive treatment of feed-forward neural networks from the perspective of statistical pattern recognition. After introducing the basic concepts, the book examines techniques for modeling probability density functions and the properties and merits of the multi-layer perceptron and radial basis function network models. Also covered are various forms of error functions, principal algorithms for error function minimalization, learning and generalization in neural networks, and Bayesian techniques and their applications. Designed as a text, with over 100 exercises, this fully up-to-date work will benefit anyone involved in the fields of neural computation and pattern recognition.
A great book on the use of neural network as they apply to pattern recognition. This book is understandably heavy on the mathematical aspects of things, but the author does so with a grain of salt. This is definitely not a mathematics book.
Most books about neural networks are silent when it comes to less obvious details of what training feedforward networks actually does, and what the result of the network represents. This book analyzes all these details by means of statistics, and consequently gives a very solid foundation for understanding neural networks. The definitive book for feedforward neural networks - extremely good! The math-heavy treatise makes it unsuitable for a beginners book, though.
My ratings of books on Goodreads are solely a crude ranking of their utility to me, and not an evaluation of literary merit, entertainment value, social importance, humor, insightfulness, scientific accuracy, creative vigor, suspensefulness of plot, depth of characters, vitality of theme, excitement of climax, satisfaction of ending, or any other combination of dimensions of value which we are expected to boil down through some fabulous alchemy into a single digit.
This book is very out of date - it was written well before the deep learning revolution.
Like a physics book about the luminiferous aether, the only people who should read this book are historians of science and technology. They will wonder how mistaken we once were about the power and potential of deep neural networks.