PRINCIPLES OF ARTIFICIAL NEURAL NETWORKS

by Daniel Graupe

The book should serve as a text for a university graduate course or for an advanced undergraduate course on neural networks in engineering and computer science departments. It should also serve as a self-study course for engineers and computer scientists in the industry. Covering major neural network approaches and architectures with the theories, this text presents detailed case studies for each of the approaches, accompanied with complete computer codes and the corresponding computed results. The case studies are designed to allow easy comparison of network performance to illustrate strengths and weaknesses of the different networks.

238 pages, Hardcover

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 Compared to current knowledge and use of neural networks, this is somewhat out of date, but if you need an introduction into the theory behind all neural networks and machine learning, this could be a good entry point.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.