Customer Reviews

Neural Networks: Algorithms, Applications, and Programming Techniques (Computation and Neural Systems Series)

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

 

 

The book explains and deduces mathematically the working principle of many architectures, and presents commented examples (good ones) in structured English (very similar to Pascal). I used it as the basis for many NN's and felt quite satisfied in all cases.

Freeman and Skapura have written a book that I use often as a quick reference, an initial peek at some type of neural network or another. But the book is often confusing (as in the opening remarks on ART with an unnecessarily complicated diagram) and sometimes just downright sloppy (as in the discussion of the input layer to counter-propagating networks where contradictory formulas are used to describe the input normalization scheme, once on p.216 and then again, differently, on p.235, with a difference that is even more confusing.

Although the first edition of the book (maybe the only one existing) has too many printed mistakes, it is a very good book on NN.
It explains in a clear and mathematical way a lot of different kinds of NN.
It's a pity that it is missing of Genetic Algorithms applied to NN.