Rating: 
Summary: Mad Scientists everywhere, repeat after me, "IT'S ALIVE!!"
Review: I used this book to host a "brown bag" discussion group at my company a year or so ago. Like everyone else's review, I have to say this is a really clear and concise book on the theories and uses of Genetic Algorithms.When I first picked up the book, the only pseudo-AI knowledge I had was in fuzzy logic and limited exposure to neural networks. I was immediately intrigued by the book's discussion over various techniques for evolving neural architectures, weights and learning algorithms for neural networks, using genetic algorithms. But, that's just a small morsel of what the book covers. Frankly, I think the book is a gold mine.
Rating:
Summary: Brief and to the Point
Review: This book is brief and to the point. You won't find here pages of source code that you could have easily ftp'd yourself. What you will find is solid theory in a mere 224 pages. This is the quickest and best way to get up to speed on GA's there is. Which is why it is a standard textbook in the field.
Rating:
Summary: Great introduction for the uninitiated!
Review: This book is ideal for someone totally new to the field of GAs. Mitchell begins with the fundamental concepts of the simple GA and proceeds to survey a wide variety of applications. I especially enjoyed the coverage of topics related to machine intelligence, which are sometimes left out in books that focus solely on optimization. The book contains enough information for someone with programming experience to code their own GA (including suggested computer exercises), although no source code is presented. However, the background gained from reading Mitchell's book will enable an easier read of more technical books (which may include source code implementations).
Rating: 
Summary: Excellent Introduction For Beginners!
Review: This book provides an extremely good introductin to people not familiar with GA. No source code is presented; if done, the book will be a complete one.Nevertheless it provides useful guidelines for implementors.
Rating:
Summary: Great Introductory Book
Review: This book provides solid background in general GA principles and theory. In addition, the author does a good job of pointing out many interesting topics of future research. Great read for aspiring cognitive scientists!
Rating:
Summary: A Great Introduction to Genetic Algorithms
Review: This is a great place to start to learn about genetic algorithms. The writing is clear and not bogged down by jargon. The book is not overly technical; it is written for the layman and has a casual conversational style that is a pleasure to read. About half of the book is devoted to presenting examples of studies that have used genetic algorithms. These examples are interesting in themselves and also serve to illustrate the variety of genetic approaches that are available. The book also presents conflicting points of view of experts about which algorithms work best and why. This is helpful in combatting the impression that a beginner sometimes gets that everything is simple and all the answers are known.
Rating:
Summary: A Great Introduction to Genetic Algorithms
Review: This is a great place to start to learn about genetic algorithms. The writing is clear and not bogged down by jargon. The book is not overly technical; it is written for the layman and has a casual conversational style that is a pleasure to read. About half of the book is devoted to presenting examples of studies that have used genetic algorithms. These examples are interesting in themselves and also serve to illustrate the variety of genetic approaches that are available. The book also presents conflicting points of view of experts about which algorithms work best and why. This is helpful in combatting the impression that a beginner sometimes gets that everything is simple and all the answers are known.
| 
