Customer Reviews

Introduction to the Theory of Neural Computation (Santa Fe Institute Studies in the Sciences of Complexity)

5 star:		(2)
4 star:		(1)
3 star:		(0)
2 star:		(0)
1 star:		(0)

 

 

This book is written from a mathematical perspective. The book introduces the Hopfield Neural Network with history and applications. The authors solve the network problem and develop the Hebb Rule. Links are made to Ising Spin models and stochastic problems. I find this book to be one of the best written mathematical guides for Neural Networks.

This was a good survey, and well-grounded mathematically. It is kind of scattershot, and if you primarily want to do practical projects like predicting financial markets, a lot of the sections won't be relevant. But if you want a broad-based approach, emphasizing a variety of network designs fro different purposes, this book is very good.

It's not the latest book on this topic, so today, there are other texts that have more recent developments to be sure. I originally read this text about 15 years ago. But what I got from this book, that I didn't get from most, are important insights and clear understanding of the material that's covered. The authors have a deep understanding, and have teaching as their goal in writing. Most other texts in this area are lacking in one or both of those characteristics, and aren't worth the paper they are printed on.