Über die Autorin bzw. den Autor

David B. Fogel is chief executive officer of Natural Selection, Inc. in La Jolla, CA―a small business focused on solving difficult problems in industry, medicine, and defense using evolutionary computation, neural networks, fuzzy systems, and other methods of computational intelligence. Dr. Fogel’s experience in evolutionary computation spans 20 years and includes applications in pharmaceutical design, computer-assisted mammography, data mining, factory scheduling, financial forecasting, traffic flow optimization, agent-based adaptive combat systems, and many other areas. Prior to cofounding Natural Selection, Inc. in 1993, Dr. Fogel was a systems analyst at Titan Systems, Inc. (1984–1988), and a senior principal engineer at ORINCON Corporation (1988–1993).
Dr. Fogel received his Ph.D. degree in engineering sciences (systems science) from the University of California at San Diego (UCSD) in 1992. He earned an M.S. degree in engineering sciences (systems science) from UCSD in 1990, and a B.S. in mathematical sciences (probability and statistics) from the University of California at Santa Barbara in 1985. He has taught university courses at the graduate and undergraduate level in stochastic processes, probability and statistics, and evolutionary computation. Dr. Fogel is a prolific author in evolutionary computation, having published over 50 journal papers, as well as 100 conference publications, 20 contributions in book chapters, two videos, four computer games, and six books―most recently, Blondie24: Playing at the Edge of AI (Morgan Kaufmann, 2002). In addition, Dr. Fogel is coeditor in chief of the Handbook of Evolutionary Computation (Oxford, 1997) and was the founding editor-in-chief of the IEEE Transactions on Evolutionary Computation (1996–2002). He serves as editor-in-chief for the journal BioSystems and is a member of the editorial board of several other international technical journals.
Dr. Fogel served as a Visiting Fellow of the Australian Defence Force Academy in November 1997, and is a member of many professional societies including the American Association for the Advancement of Science, the American Association for Artificial Intelligence, Sigma Xi, and the New York Academy of Sciences. He was the founding president of the Evolutionary Programming Society in 1991 and is a Fellow of the IEEE, as well as an associate member of the Center for the Study of Evolution and the Origin of Life (CSEOL) at the University of California at Los Angeles. Dr. Fogel is a frequently invited lecturer at international conferences and a guest for television and radio broadcasts. His honors and awards include the 2001 Sigma Xi Southwest Region Young Investigator Award, the 2003 Sigma Xi San Diego Section Distinguished Scientist Award, the 2003 SPIE Computational Intelligence Pioneer Award, and the 2004 IEEE Kiyo Tomiyasu Technical Field Award.

Von der hinteren Coverseite

This Third Edition provides the latest tools and techniques that enable computers to learn

The Third Edition of this internationally acclaimed publication provides the latest theory and techniques for using simulated evolution to achieve machine intelligence. As a leading advocate for evolutionary computation, the author has successfully challenged the traditional notion of artificial intelligence, which essentially programs human knowledge fact by fact, but does not have the capacity to learn or adapt as evolutionary computation does.

Readers gain an understanding of the history of evolutionary computation, which provides a foundation for the author's thorough presentation of the latest theories shaping current research. Balancing theory with practice, the author provides readers with the skills they need to apply evolutionary algorithms that can solve many of today's intransigent problems by adapting to new challenges and learning from experience. Several examples are provided that demonstrate how these evolutionary algorithms learn to solve problems. In particular, the author provides a detailed example of how an algorithm is used to evolve strategies for playing chess and checkers.

As readers progress through the publication, they gain an increasing appreciation and understanding of the relationship between learning and intelligence. Readers familiar with the previous editions will discover much new and revised material that brings the publication thoroughly up to date with the latest research, including the latest theories and empirical properties of evolutionary computation.

The Third Edition also features new knowledge-building aids. Readers will find a host of new and revised examples. New questions at the end of each chapter enable readers to test their knowledge. Intriguing assignments that prepare readers to manage challenges in industry and research have been added to the end of each chapter as well.

This is a must-have reference for professionals in computer and electrical engineering; it provides them with the very latest techniques and applications in machine intelligence. With its question sets and assignments, the publication is also recommended as a graduate-level textbook.

Aus dem Klappentext

This Third Edition provides the latest tools and techniques that enable computers to learn

The Third Edition of this internationally acclaimed publication provides the latest theory and techniques for using simulated evolution to achieve machine intelligence. As a leading advocate for evolutionary computation, the author has successfully challenged the traditional notion of artificial intelligence, which essentially programs human knowledge fact by fact, but does not have the capacity to learn or adapt as evolutionary computation does.

Readers gain an understanding of the history of evolutionary computation, which provides a foundation for the author's thorough presentation of the latest theories shaping current research. Balancing theory with practice, the author provides readers with the skills they need to apply evolutionary algorithms that can solve many of today's intransigent problems by adapting to new challenges and learning from experience. Several examples are provided that demonstrate how these evolutionary algorithms learn to solve problems. In particular, the author provides a detailed example of how an algorithm is used to evolve strategies for playing chess and checkers.

As readers progress through the publication, they gain an increasing appreciation and understanding of the relationship between learning and intelligence. Readers familiar with the previous editions will discover much new and revised material that brings the publication thoroughly up to date with the latest research, including the latest theories and empirical properties of evolutionary computation.

The Third Edition also features new knowledge-building aids. Readers will find a host of new and revised examples. New questions at the end of each chapter enable readers to test their knowledge. Intriguing assignments that prepare readers to manage challenges in industry and research have been added to the end of each chapter as well.

This is a must-have reference for professionals in computer and electrical engineering; it provides them with the very latest techniques and applications in machine intelligence. With its question sets and assignments, the publication is also recommended as a graduate-level textbook.

Auszug. © Genehmigter Nachdruck. Alle Rechte vorbehalten.

Evolutionary Computation

John Wiley & Sons

Chapter One

1.1 BACKGROUND

Calculators are not intelligent. Calculators give the right answers to challenging math problems, but everything they "know" is preprogrammed by people. They can never learn anything new, and outside of their limited domain of utility, they have the expertise of a stone. Calculators are able to solve problems entirely because people are already able to solve those same problems.

Since the earliest days of computing, we have envisioned machines that could go beyond our own ability to solve problems-intelligent machines. We have generated many computing devices that can solve mathematical problems of enormous complexity, but mainly these too are merely "calculators." They are preprogrammed to do exactly what we want them to do. They accept input and generate the correct output. They may do it at blazingly fast speeds, but their underlying mechanisms depend on humans having already worked out how to write the programs that control their behavior. The dream of the intelligent machine is the vision of creating something that does not depend on having people preprogram its problem-solving behavior. Put another way, artificial intelligence should not seek to merely solve problems, but should rather seek to solve the problem of how to solve problems.

Although most scientific disciplines, such as mathematics, physics, chemistry, and biology, are well defined, the field of artificial intelligence (AI) remains enigmatic. This is nothing new. Even 20 years ago, Hofstadter (1985, p. 633) remarked, "The central problem of AI is the question: What is the letter 'a'? Donald Knuth, on hearing me make this claim once, appended, 'And what is the letter 'i'?'-an amendment that I gladly accept." Despite nearly 50 years of research in the field, there is still no widely accepted definition of artificial intelligence. Even more, a discipline of computational intelligence-including research in neural networks, fuzzy systems, and evolutionary computation-has gained prominence as an alternative to AI, mainly because AI has failed to live up to its promises and because many believe that the methods that have been adopted under the old rubric of AI will never succeed.

It may be astonishing to find that five decades of research in artificial intelligence have been pursued without fundamentally accepted goals, or even a simple but rigorous definition of the field itself. Even today, it is not uncommon to hear someone offer, in a formal lecture, that artificial intelligence is difficult to define, followed by absolutely no attempt to define it, followed by some interesting research on a problem for which a better solution has been found by some method that is then deemed to be artificially intelligent.

When definitions have been offered, they have often left much to be desired. Intelligent machines may manipulate symbols to solve problems, but simple symbol manipulation cannot be the basis for a broadly useful definition of artificial intelligence (cf., Buchanan and Shortliffe, 1985, p. 3). All computers manipulate symbols; at the most rudimentary level these are ones and zeroes. It is possible for people to assign meaning to these ones and zeroes, and combinations of ones and zeroes, but then where is the intelligence? There is no fundamental difference between a person assigning meaning to symbols in a computer program and a person assigning meaning to binary digits manipulated by a calculator. Neither the program nor the calculator has created any symbolic meaning on its own.

Waterman (1986, p. 10) offered that artificial intelligence was "the part of computer science concerned with developing intelligent computer programs." This tautological statement offers no basis for designing an intelligent machine or program.

Rich (1983, p. 1) offered, "Artificial intelligence (AI) is the study of how to make computers do things at which, at the moment, people are better," which was echoed even as recently as 1999 by Lenat (in Moody, 1999). But this definition, if regarded statically, precludes the very existence of artificial intelligence. Once a computer program exceeds the capabilities of a human, the program is no longer in the domain of AI.

Russell (quoted in Ubiquity, 2004) offered, "An intelligent system is one whose expected utility is the highest that can be achieved by any system with the same computational limitations." But this definition appears to offer intelligence to a calculator, for there can be no higher expected utility than getting four as the right answer to two plus two. It might even extend to a pebble, sitting at equilibrium on a bottom of a pond, with no computational ability whatsoever. It is no wonder that we have not achieved our dreams when our efforts have been defined so poorly.

The majority of definitions of artificial intelligence proffered over decades have relied on comparisons to human behavior. Staugaard (1987, p. 23) attributed a definition to Marvin Minsky-"the science of making machines do things that would require intelligence if done by men"-and suggested that some people define AI as the "mechanization, or duplication, of the human thought process." Using humans as a benchmark is a common, and I will argue misplaced, theme historically in AI. Charniak and McDermott (1985, p. 6) offered, "Artificial intelligence is the study of mental faculties through the use of computational models," while Schildt (1987, p. 11) claimed, "An intelligent program is one that exhibits behavior similar to that of a human when confronted with a similar problem. It is not necessary that the program actually solve, or attempt to solve, the problem in the same way that a human would."

What then if there were no humans? What if humans had never evolved? Would this preclude the possibility of intelligent machines? What about intelligent machines on other planets? Is this precluded because no humans reside on other planets? Humans are intelligent, but they are only one example of intelligence, which must be defined properly in order to engage in a meaningful discourse about the possibility of creating intelligent machines, be they based in silicon or carbon. I will return to this point later in this chapter.

The pressing question, "What is AI?" would become mere semantics, nothing more than word games, if only the answers did not suggest or imply radically different avenues of research, each with its own goals. Minsky (1991) wrote, "Some researchers simply want machines to do the various sorts of things that people call intelligent. Others hope to understand what enables people to do such things. Still other researchers want to simplify programming." That artificial intelligence is an extremely fragmented collection of endeavors is as true today as it was in 1991. Yet the vision of what is to be created remains prominent today, even as it did when Minsky (1991) wrote: "Why can't we build, once and for all, machines that grow and improve themselves by learning from experience? Why can't we simply explain what we want, and then let our machines do experiments or read some books or go to school, the sorts of things that people do. Our machines today do no such things."

The disappointing reality is that, actually, even in 1991 machines did indeed do many of these things and the methods that...