Rating: 
Summary: Most compelling AI book I've read
Review: I was already interested in neural networks, and have read several other books on the subject, all for information on how to design and build neural networks to do various tasks, so I was primed to like this book, but I had no idea how compelling it would be. Fogel does give most of the details necessary to recreate Blondie, but some of the specifics for the later modifications are missing and can be found, I believe, in his and his partner's scientific articles referenced in the book.The first half is quite good, giving very basic background information on neural networks and machine learning algorithms as well as a brief history of the two best known checkers programs, Samuels' machine learning checkers player and Chinook, the best ever player (so far). It's the second half of the book, however, that kicks the story into overdrive. Fogel begins describing how he and his partner, Kumar Chellapilla, made their design decisions, evolved a neural net, then began playing it against humans over the internet. Even if you aren't all that interested in checkers (I am not) the games as they are described by Fogel become at least as interesting as any close sporting event, especially in those cases where the neural net set up traps for its opponents that neither Fogel nor the other player could foresee. There were times that I couldn't stop reading. I'd get off the bus to work, get in the office, and continue until I could pull myself away. The second half of this book is as much a page turner as the best novels I've read. An absolute must read for anyone interested in where AI needs to go.
Rating:
Summary: Very Worthwhile Book
Review: I'm about 3/4 of the way through this book and I am enjoying it immensely; so much so I wish I had saved it for vacation! I work in the field of A.I. so this book is of special interest to me, but I think it's one of this year's "must-read" popular science books. The book is written in a colloquial style, but manages to give both a good introduction to evolutionary artificial intelligence and computer game design -- science entertainment without the fluff! The first-hand view of the tension between scientific rigor and engineering excitement will be especially interesting to prospective young scientists (hint: rigor wins). I hope the publisher has an active campaign to market this book as a educational tool. I met Larry Fogel in a business situation a number of years ago, and one of the things I remember most was his contagious enthusiasm for his work and research. David Fogel communicates the same enthusiasm in this book. Don't pass it by.
Rating: 
Summary: A very interesting and engaging story
Review: In this book the author gives a detailed story of his involvement in the development of the "Blondie24" checkers program, and the story is a very interesting one. The reader not familiar with certain research topics in artificial intelligence such as neural networks and evolutionary programming, will still be able to read the book since the author gives a good intuitive discussion of these topics. If the book inspires a young person to enter the field of artificial intelligence, it has served a noble purpose, even if the author did not intend this as the primary purpose of the book. The author's main thesis is the value of using concepts of evolutionary programming to bring about the rise of intelligent machines. The author clearly believes that before "HAL-like" machines can be built, researchers must construct computer programs that can teach themselves how to solve problems without any help. Intelligent machines must be creative, and learn and adapt to new circumstances. Traditional research in artificial intelligence has been geared towards building machines that emulate human intelligence, and this will not do in the author's view. The research did not address the true definition and meaning of intelligence, but instead made the goal of creating machines that think and act like humans, whence the famous "Turing test" for machine intelligence. The author completely rejects this test and holds it responsible for bringing about the "AI winter" where no substantive progress was made. "The key to creating truly creative computers", he says, "lies in mimicking nature's process of evolution." The author though was not comfortable with merely refuting arguments about the Turing test or other strategies for designing intelligent machines. He knows that such argument-counterargument activity will not result in sound approaches to artificial intelligence. Therefore, he sought to construct a working, viable alternative, which produces results that can be checked. Intelligence for the author is based on decision making, such as how to obtain resources, and how to respond to environmental changes by prioritizing goals. "Intelligence is the property that allows living organisms to sense, react to, and learn from their environment in order to adapt their behavior to better promote their survival", he says. Hence, the author brings in the evolutionary paradigm to artificial intelligence, and to give credence to his view, he attempts to create a program that will learn the game of checkers and then play it well, at least from the standpoint of the checkers game rating system. The book is a very detailed overview of how he and his collaborators went about doing this, the most interesting strategy being the use of neural networks, the topology of which is not set beforehand, but is evolved according to a "survival of the fittest" process. The author, through diagrams, gives the reader a taste of the moves that were made as the program dealt with online checkers games. The author even gives a dose of the criticism he received from referees when his results were submitted to professional journals, and this gives the book greater appeal from the standpoint of intellectual honesty. Certainly the author and those he worked with have achieved a great deal in the context of building intelligent machines. It remains to be seen whether evolutionary programming can be extended to situations that require even more creativity, such as that of generating new and interesting results in pure mathematics. This is the ultimate test in my view of machine intelligence. It is not immediately obvious how this is to be done in the evolutionary programming or indeed of any other paradigm in artificial intelligence.
Rating:
Summary: Best AI Story to date
Review: Story is full of good scienctific thought and contains enough meat to interest someone learning about AI. If you're familiar with some of the technology you'll race through the first half quickly, but the progression of blondie in the second half is well worthwhile for the excitement of the challenge they set themselves and also the psychology of their opponents. A little bit pricy for the size, but good value for the content, and if you're really interested you'll probably buy it anyway.
Rating:
Summary: A Leap of Insight into Artificial Intelligence.
Review: The "Leap Of Insight"; Perhaps nothing demonstrates high intelligence more than the ability to bring together the elements of a problem into a solution that no one has ever seen before. The leap of insight extends far beyond teaching or learning; it is the essence of intelligence that expands the body of knowledge as a whole. 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.
Rating:
Summary: Who is the genius: David or Blondie?
Review: The most enthralling account of what otherwise could have been a dry discussion of some arcane research. I have a couple of whimsical comments before I get on to the review proper. David and Kumar played Blondie24, a computer program, against human opponents on a web site. They found that when they played using their own names, they were not invited to play many games. When they changed the name they used to that of a Star Wars(tm) character, they became more popular. However it was only when they started using 'Blondie24' as a name that everyone wanted to play them. This lesson was not lost on David when it came to naming his book...:) In an early part of the book, David discusses the Turing test, which involves fooling a human observer into believing that a man, hidden from the observer, is actually a woman, based on responses to the observer's questions. Replace the man with a machine and repeat the experiment. David and Kumar seem to have run a little Turing test of their own. Humans at the checkers web site believed they were playing against another human, not a computer program. Indeed they were fooled into thinking they were playing a young woman, not a couple of frizz-haired mad scientists. (Please note I have no direct evidence to support my description of David and Kumar.) An Artificial Neural Network/minimax program, Blondie24, learns to play checkers at expert level without being taught, without access to the vast human knowledge of the game. Significantly, Blondie24's game relies on n-ply position evaluation without recourse to an end-game database or opening book. The work of David and Kumar demonstrates that a solution to a problem is not always a necessary precursor to developing a computer program. Let the program find the solution on its own. David's book is an entertaining and elucidating account of the development of Blondie24, a program that taught itself to play checkers. In it, he discusses why traditional AI research has been less than spectacularly successful and proposes a new direction: evolutionary computation. To prove the validity of this approach, he and his colleague Kumar develop a program that through the process of evolution through natural selection, learns to play checkers at expert level. Blondie24 was put through its paces at a checkers web site, where it attained a level of 'expert'. Human players, who believed they were competing with a lady, blonde, 24, math major, were engaged in games over a period to determine how effectively the evolutionary computation approach had developed a competitive checkers player. This section of the book makes gripping reading, unlike this review. I've had the opportunity to play Blondie24, which is now available as a PC game, and can attest to the strength of its game. There are four 'difficulty' levels, from novice to expert, so it suits all players. Not only does it play a great game, the presentation which revolves around film footage of your opponent, can be sometimes hilarious and sometimes infuriating. It is interesting to try and imagine what the program is doing while you are playing it. I urge everybody with even a passing interest in the field of AI to purchase this book. Read it and then consider: is the genius David (and Kumar), who developed this program, or Blondie24, a program that taught itself to play checkers at a level much higher than its creators. The serious AI researcher should also consider David's other books, also available at amazon.
Rating:
Summary: What does "Intelligent" mean?
Review: This book has the technical background to make it of serious import to those in the field, while at the same time it's perfectly accessible to laypeople like me. And as a layperson, I must say the concepts excite me, and this book certainly got me excited about the possibilities in this field of study. It's making me regret (just a little) the fact that I'm a businessperson instead of an academic. The definition of an intelligent machine, so crisply laid out for us here, reveals the common misconceptions of so-called smart machines like IBM's Deep Blue, and its resulting negative impact upon the quest for a real "learning machine". As far away from the predictions of a HAL as we were in the year 2001, with David Fogel's help the real HAL may be closer than we think. I couldn't put this down.
Rating:
Summary: Fascinating insight into "Real" AI
Review: This book is a must-read for anyone even remotely interested in Artificial Intelligence. Blondie24 is the story of how real machine learning created an expert checkers playing program. Instead of the traditional method of hand-coding human expertise about a game, Fogel set out from the start to have his program learn to play checkers without any human coaching except for the basic rules of the game. Starting from nothing but randomness, different checker playing program candidates competed with each other in a "survival of the fittest" tournament, evolving better players over time. The end result was an expert-level checkers-player.
As Dr. Fogel eloquently points out, the most impressive thing about Blondie24 is not the high level of play it achieved but the methodology used to get there. Computer programs that can teach themselves to solve problems!
A very readable book on a fascinating topic.
Rating:
Summary: Great Stuff
Review: This book should probably appeal to almost anyone with an interest in artificial intelligence. 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.
Rating:
Summary: An inspiring story about an artificially evolved algorithm
Review: This book tells you the story of a computer algorithm that, in the words of the author, "taught itself to play checkers". The second section, which contains the core of the book, is organized as an abridged diary that describes the steps taken to create this program and to test it in rated competition under the name of Blondie24 against human opponents at an online gaming site. Since the book is aimed at a general audience, the first section introduces all the relevant knowledge required to fathom the rest of the book. This section introduces the purpose of artificial intelligence, the demystification of the all-famous computer Deep Blue that defeated chess champion Garry Kasparov, the basics of artificial neural networks and of the game of checkers, and a survey of previous attempts at producing computer programs to play checkers. The last chapter in this preparatory section states the two fundamental questions that the author (David B. Fogel) and his partner in this endeavor (Kumar Chellapilla) set out to answer when they started to build their own checkers program, which can be phrased as: (1) Can a computer program learn on its own the features important to play checkers at the level of a human expert? (2) Can this learning be achieved by just playing games against itself and receiving feedback only after a series of games without even knowing which games were won or lost but only how many? Their approach consisted of using an idea borrowed from "mother nature" that only until recently has started to be embraced by the scientific community in the field of artificial intelligence. This idea is evolution. By combining random mutation with selection over a "population" of checkers-playing artificial neural networks that played against each other they obtained after 250 generations a program that was able to reach the expert-level rating and that even scored a few victories against human players rated at the master-level. Most technical details are left out in order to make the text accessible to a wider audience. However, in the spirit of being a scientific document, there are references to all relevant scientific papers in case you want to do further research. The writing style is both engaging and easy to follow. In addition to the main text of the book, there is a wealth of notes in a special section at the end of the book which the author uses to expand on specific topics that might be of interest to the reader. It is for this separate notes section that you might benefit from using two bookmarks, instead of just one, while you read the book. There is also an interesting section in which the author addresses a series of objections that have been raised against the ideas he discusses in this book. In my opinion, the only weakness of the book is that it spends too much ink in telling you about the moves that Blondie24 (and its siblings) made in some specific games. This will be of interest to you only if you are keen on checkers. If you have an academic training equivalent to a B.S. in Computer Science you will have the additional benefit of ending up with a clear picture of how to reproduce the ideas used to create Blondie24, although no computer code is offered. The idea they use is so simple and yet so powerful that you'll be temped to jump into the bandwagon of evolutionary computation after reading this book.
| 
