Practical Neural Network Recipies in C++

Preface

The primary purpose of this book is to serve as a cookbook for neural

network solutions to practical problems. It should enable people with

moderate programming experience to select a neural network model

that is appropriate to solving a particular problem and to produce a

working program that implements that network. It will also provide

guidance along the entire problem-solving path. This includes

designing the training set, preprocessing variables, training and

validating the network, and evaluating its performance. A detailed

discussion of computation of decision confidences is also provided.

One of the thorniest issues in neura ...