Blondie24: Playing at the Edge of AI

Author: David Fogel, David B. Fogel List Price: $26.95 Our Price: Click to see the latest and low price ISBN: 1558607838 Publisher: Morgan Kaufmann (22 September, 2001) Edition: Paperback Sales Rank: 53,656 Average Customer Rating: 4.67 out of 5

Buy now directly from Amazon.com -

Customer Reviews

To be truly intelligent, Artificial Intelligence must demonstrate the ability to see characteristics and features of problem elements that transcends the initial program. In Blondie24, David Fogel and Kumar Chellapilla show through their own leap of insight that evolved neural networks can dramatically exceed the knowledge set embedded by the programmers.

This engaging story of David and Kumar's journey to prove that true Artificial Intelligence is within the art of the possible will entertain and capture the readers' attention, regardless of the readers' knowledge of computer science.

For the beginner this book offers a nice intuitive introduction to subject areas such as neural nets and genetic algorithms.

The expert is not likely to learn any technical matertial but will probably enjoy it as it is a wonderfully written story and perhaps some inspiration. If all you want is a technical manual, then you should look elsewhere.

My level of knowledge of AI is closer to a beginner than an expert. Here are three things that struck me:

1. How long it can take to evolve a good solution. One example from the book took 6 months using pentium 400.

2. How petty academics can be. The last section contains comments made by referees reviewing papers written by the author in scientific journals. Most of them smack of "Damn why didn't I think of that. Well since I didn't, I will try to block someone who did".

3. How elegant GA can be. This book has inspired me to seriously study the various techniques in evolutionary methods.

There are two minor annoyances I found in the book. They are both related to the layout of the book. The book is almost square and has relatively short sides. I assume this was done to make the book look like a checkerboard. This gives the book an odd "feel". Because of the dimentions, the amount of material on each page is relatively small and often the diagrams are not on the same page as the words describing them. However these are very minor complaints on what is a very fine book.

You'll find a lot of books in this field to be written from a point of view of someone who develops neural networks for a living (as opposed to using them when needed as a tool), and so are chock full of the kinds of equations and maths that I'm sure are obvious after you've written two or three of the things, but not much good for us first-timers to understand.

That is not Mr. Fogel's book.

Fogel goes to great pains to steer well clear of equations altogether and, although there's enough detail in there to start building your own networks, it's there in plain English, spelled out carefully but not condescendingly.

I guess the highest praise I can give is that while a lot of the other books (I read four) left me more confused than when I went in, I finished Mr. Fogel's book and felt immediately able to start plugging away at building genetically evolved neural networks myself.

Similar Products