Scan barcode
wwatts1734's review
4.0
John H. Holland is a major researcher in the field of artificial intelligence and the father of one of AI's most popular methodologies, the genetic algorithm. In this book, Holland explores the concept of emergence in complex systems. Complex systems are those systems that have multiple components, and as those components interact with each other they create exponentially increasing numbers of possible states of the system. So how does the researcher model a system such as this? Holland explains that studying the emergence, or the process by which the individual components meld into the complex system, is critical to understanding any complex system.
So how does one study emergence? This is as complicated an issue as the study of complex systems themselves. Holland discusses several methods. He goes through traditional stochastic models such as the random walk and the biased random walk model. He explores the mathematical models used to study such systems, such as difference and differential equations. But the most powerful discussion in this book is the discussion on artificial intelligence techniques. These are interative processes that mimic biological processes, such as the neural network and the genetic algorithm. These processes develop a "memory", which allows the process not only find the right answer but to remember what it did to find the right answer so that it can use the same method the next time. Such systems do not need to understand the mathematics behind a process, just the results. That is the allure of artificial intelligence.
Holland uses complicated mathematical models and concepts so this really is not appropriate for the novice. But Holland's writing style is good and he makes the topics interesting, drawing on metaphors and analogies to explain complicated subjects. He brings in discussions from physics and biology, and spends a considerable amount of time discussing games like checkers and chess. He even draws examples from literature and poetry. At the end of this discussion, the reader really feels comfortable with the breadth of the applicability of these theories.
I would recommend this work for anyone who is interested in the dynamics of complex systems or in artificial intelligence.
So how does one study emergence? This is as complicated an issue as the study of complex systems themselves. Holland discusses several methods. He goes through traditional stochastic models such as the random walk and the biased random walk model. He explores the mathematical models used to study such systems, such as difference and differential equations. But the most powerful discussion in this book is the discussion on artificial intelligence techniques. These are interative processes that mimic biological processes, such as the neural network and the genetic algorithm. These processes develop a "memory", which allows the process not only find the right answer but to remember what it did to find the right answer so that it can use the same method the next time. Such systems do not need to understand the mathematics behind a process, just the results. That is the allure of artificial intelligence.
Holland uses complicated mathematical models and concepts so this really is not appropriate for the novice. But Holland's writing style is good and he makes the topics interesting, drawing on metaphors and analogies to explain complicated subjects. He brings in discussions from physics and biology, and spends a considerable amount of time discussing games like checkers and chess. He even draws examples from literature and poetry. At the end of this discussion, the reader really feels comfortable with the breadth of the applicability of these theories.
I would recommend this work for anyone who is interested in the dynamics of complex systems or in artificial intelligence.
caterinaanna's review against another edition
4.0
Not a light or easy read, even if you choose to ignore the maths in the boxes, but worth the effort. By sticking to a few of the many possible examples and explaining them in detail, Holland shows how complex behaviours can emerge from the repeated application of a few simple rules and how this behaviour can appear directed when constrained. I'm sure field has moved on since this was written, and perhaps some of the ideas in here are out of date or have led to dead ends, but that he doesn't claim to have all the answers is something that makes the book a refreshing change from the gee-whiz popular science books that I seem to pick up more often. I don't usually need to make use of a pencil and paper when reading these days, but didn't resent having to do so in this case.