Principles Of Artificial Neural Networks (3rd Edition)

by Daniel Graupe

Artificial neural networks are most suitable for solving problems that are complex, ill-defined, highly nonlinear, of many and different variables, and/or stochastic. Such problems are abundant in medicine, in finance, in security and beyond.

This volume covers the basic theory and architecture of the major artificial neural networks. Uniquely, it presents 18 complete case studies of applications of neural networks in various fields, ranging from cell-shape classification to micro-trading in finance and to constellation recognition — all with their respective source codes. These case studies demonstrate to the readers in detail how such case studies are designed and executed and how their specific results are obtained.

The book is written for a one-semester graduate or senior-level undergraduate course on artificial neural networks. It is also intended to be a self-study and a reference text for scientists, engineers and for researchers in medicine, finance and data mining.

Contents: Introduction and Role of Artificial Neural Networks Fundamentals of Biological Neural Networks Basic Principles of ANNs and Their Early Structures The Perceptron The Madaline Back Propagation Hopfield Networks Counter Propagation Large Scale Memory Storage and Retrieval (LAMSTAR) Network Adaptive Resonance Theory The Cognitron and the Neocognitron Statistical Training Recurrent (Time Cycling) Back Propagation Networks
Readership: Graduate and advanced senior students in artificial intelligence, pattern recognition & image analysis, neural networks, computational economics and finance, and biomedical engineering.

384 pages, Kindle Edition

First published July 15, 1997

Reviews

[Mike · Rating 4 out of 5]

This is a challenging introduction to artificial neural networks by using a number of networks through history as case studies. I used this book as a companion for a course taught by the author. The course itself was excellent, and very challenging. The book contained invaluable examples, however the descriptions were fairly brief. It is interesting in the history of the evolution of neural networks, and to use as a reference. Compared to current knowledge and use of neural networks, this is somewhat out of date, but if you need an introduction into the theory behind all neural networks and machine learning, this could be a good entry point.

[Izhan Noorzi · Rating 3 out of 5]

Taking into consideration, this is a basic book for neuroscience scholars.