:santagrin: This book was suggested by Percy Tiglao

Book excerpts:

This notes cover an introduction to neural networks in which basic concepts, techniques and ideas are given priority over lengthy mathematical proofs and technical detail. After an introduction and review of notation, several basic models are introduced starting with the TLU and progressively presenting more advanced models.

The notes is not specifically aimed towards computer science students, since it also has other backgrounds in mind. It does however requires a sufficient background in science/math (basic algebra and geometry and vectors).

This book has formed the basis of a book, An Introduction to Neural Networks, which contains a significant increase in material, including sections on ART, RBFs, PCA, digital nodes, alternative views of network function, applications, plus many more diagrams, etc.

Contents:

1 - Computers and Symbols versus Nets and Neurons
2 - TLUs and vectors - simple learning rules
2(s) - TLUs and vectors - summary
3 - The delta rule
4 - Multilayer nets and backpropagation
5 - Associative memories - the Hopfield net
6 - Hopfield nets (contd.)
7 - Competition and self-organisation - Kohonen nets
8 - Alternative node types
9 - Cubic nodes (contd.) and Reward Penalty training
10 - Drawing things together - some perspectives

Reviews:

Amazon.com

:) "Although this is by no means a comprehensive book for those who are taking a high level course on AI/neural nets it serves as a very good and complete introduction to those of us who wish to learn more about a very interesting area of computing."