This site was actively maintained from 1996-2006. However, by 2006 the CAS/AL/ABM/ACE literature was growing at a rapid rate, making it difficult to maintain this broad a coverage. Since 2006 attention has been more narrowly focused on CAS/AL/ABM/ACE-related materials of possible interest to ACE researchers. For annotated pointers to research on evolutionary learning algorithms, visit:
ACE Research Area: Learning and the Embodied Mind.
2.A Introductory Readings on
Evolutionary Computation
Peter Angeline, Robert Reynolds, John R. McDonnell, and Russell Eberhart
(eds.), Evolutionary Programming VI: Proceedings of the Sixth
International Conference on Evolutionary Programming, Spring-Verlag,
1997, ISBN 30540-62788-X.
Thomas Bäck, Evolutionary Algorithms in Theory and Practice:
Evolution Strategies, Evolutionary Programming, Genetic Algorithms,
Oxford Univ. Press, 1996.
T. Bäck, David Fogel, and Zbigniew Michalewicz (eds.),
Handbook of Evolutionary Computation,
Oxford Univ. Press, 1997,
ISBN: 0-7503-0392-1.
Regularly updated handbook covering the theory and
application of evolutionary computation.
Paul R. Cohen, Empirical Methods for Artificial
Intelligence, The MIT Press, 422pp., 1995, ISBN: 0-262-03225-2.
From the publisher: "Computer science and artificial
intelligence in particular have no curriculum in research methods,
as other sciences do. This book presents empirical methods for
studying complex computer programs: exploratory tools to help find
patterns in data; experiment designs and hypothesis-testing tools to
help data speak convincingly; and modelling tools to help explain
data. Although many of these techniques are statistical, the book
discusses statistics in the context of the broader empirical
enterprise. ... Mathematical details are confined to appendices and
no prior knowledge of statistics or probability theory is assumed."
Paul R. Cohen is a Professor in the Department of Computer
Science and a Director of the Experimental Knowledge Systems
Laboratory at the University of Massachusetts, Amherst.
James P. Crutchfield and Peter Schuster (eds.), Evolutionary
Dynamics: Exploring the Interplay of Selection, Accident,
Neutrality, and Function, Oxford University Press, New York,
N.Y., 480 pp., November 2002. ISBN 0-195-14264-0
From the Publisher: "This book is an assessment and review
of the recent progress in integating evolutionary modeling and
computation, molecular and developmental evolution, and nonlinear
population dynamics into evolutionary theory. It brings together a
wide range of eminent researchers in evolutionary dynamics in order
to formulate a comprehensive theory that builds on nonlinear
mathematics and physics. The text is divided into four sections:
macroevolution; epochal evolution; population genetics, dynamics,
and optimization; and evolution of cooperation, each containing
several in-depth chapters and discussions."
James P. Crutchfield is a theoretical physicist and Research
Professor at the Santa Fe Institute. Peter Schuster is Professor of
Theoretical Chemistry at the University of Vienna and an external
faculty member of the Santa Fe Institute.
Kenneth A. De Jong, Evolutionary Computation, MIT Press, A
Bradford Book, April 2001, 272 pages, ISBN: 0-262-04194-4.
From the publisher: "This book offers a clear and comprehensive
introduction to the field of evolutionary computation: the use of
evolutionary systems as computational processes for solving complex problems.
Over the past decade, the field has grown rapidly as researchers in
evolutionary biology, computer science, engineering, and artificial life have
furthered our understanding of evolutionary processes and their application in
computational systems. Although many excellent books have covered specific
areas of evolutionary computations, this one is noteworthy for approaching
genetic algorithms, evolution strategies, genetic programming, and so on as
specific instances of a more general class of evolutionary algorithms."
Kenneth A. De Jong is Professor of Computer Science at George Mason
University.
A. E. Eiben and Zbigniew Michalewicz (eds.),
Evolutionary Computation, IOS Press, 1999, 266 pp., $86. ISBN
9-05199-471-1
From the editors: "Evolutionary algorithms (EA) have received
considerable attention regarding their potential for solving real-world
problems involving various types of tasks. ... These include numerical and
combinatorial optimization, machine learning, optimal control, cognitive
modeling, classical operation research problems (travelling salesman
problem, knapsack problems, transportation problems, assignment problems, bin
packing, scheduling, partitioning, etc.), engineering design, system
integration, iterated games, robotics, signal processing and many others.
The editors of this book are proud to present a collection of papers that
reflects the diversity of the field of evolutionary computing."
A. E. Eiben is with the Leiden Center for Natural Computing,
Leiden University, The Netherlands. Zbigniew Michalewicz is with the
University of Carolina, Charlotte, North Carolina, USA.
David B. Fogel, Evolutionary Computation: Principles and Practice for
Signal Processing, Society of Photo-Optical Instrumentation Engineers
(SPIE) Press, Volume TT43, July 2000, 182 pages, ISBN: 0-819-43725-5.
From the Author: "This book provides a comprehensive introduction to
evolutionary computation, as well as an overview of the application of
evolutionary algorithms to problems in signal processing, including time
series prediction and modelling using autoregressive-moving average (ARMA)
and neural network models of data. Efforts to apply evolutionary algorithms
to clustering, classification, and control are also explored in various
regards, including cases that involve sonar data, mammographic data, and
freeway traffic flow control. The book concludes by discussing the theory
and tools that can be useful for tailoring improved evolutionary algorithms
for specific applications, particularly relying on the use of fitness
distributions of operators."
The book is intended to serve as an undergraduate or graduate text
that supplements traditional textbooks on signal processing and as a useful
monograph for engineers involved in signal processing, pattern recognition,
and control.
Dr. David B. Fogel is the CEO of Natural Selection, Inc.
(La Jolla, California), a company which applies evolutionary computation to a
wide variety of real-world problems. He is also the founder of the
Evolutionary Programming Society and past-editor of the IEEE Transactions
on Evolutionary Computation.
David B. Fogel, Evolutionary Computation: Toward a New Philosophy
of Machine Intelligence, IEEE Press, Piscataway, NJ, 1995.
David B. Fogel, Evolutionary Computation: The Fossil
Record, The IEEE Press, 1998, 650 pages, ISBN 0-7803-3481-7.
This book is a collection of reprinted papers from the
history of simulated evolution dating back to the early/mid-1950s.
Each chapter has an introduction that places the reprint in the
context of present and prior work. All of the introductions are
based on interviews conducted by Fogel with the original
authors (if still alive) and their colleagues over a period of four
years.
Lawrence J. Fogel, Peter Angeline, and Thomas Baeck (eds.), Evolutionary
Programming V: Proceedings of the Fifth Annual Conference on Evolutionary
Programming, MIT Press, Cambridge, 1996.
Michael Luck, Peter McBurney, and Chris Preist (eds.), Agent
Technology: Enabling Next Generation Computing, AgentLink, 102pp.,
January 2003, ISBN: 0-854-32788-6.
From Michael Luck (AgentLink Director): "This report describes the
current state-of-the-art of agent technologies and identifies trends and
challenges that will need to be addressed over the next 10 years to progress
the field and realise the benefits. It offers a roadmap that is the result
of discussions among participants from over 150 organisations including
universities, research institutions, large multinational corporations and
smaller IT start-up companies. The roadmap is a living document and will
continue to be developed over time, identifying successes and challenges, and
pointing to future possibilities and demands."
Michael Luck is Professor of Computer Science, University of
Southampton, UK. Peter McBurney is with the Department of Computer Science,
University of Liverpool, UK. Chris Preist is with Hewlett-Packard Company,
Bristol, UK.
Zbigniew Michalewicz and David B. Fogel, How to Solve It,
Springer-Verlag, N.Y., 1999, 480 pp., ISBN 3-540-66061-5.
From the publisher: "This book is the only source that provides
comprehensive, current, and detailed information on problem solving using
modern heuristics. It covers classic methods of optimization, including
dynamic programming, the simplex method, and gradient techniques, as well as
recent innovations such as simulatated annealing, tabu search, and
evolutionary computation. Integrated into the discourse is a series of
problems and puzzles to challenge the reader."
Zbigniew Michalewicz is with the Department of Computer Science,
University of North Carolina, Charlotte, and David Fogel is with
Natural Selection, Inc., La Jolla, California.
Mukesh Patel, Vasant Honavar, and Karthik Balakrishnan (Eds.),
Advances in the Evolutionary Synthesis of Intelligent Agents,
The MIT Press, 455 pp., March 2001, ISBN: 0-262-16201-6.
From the publisher: "This book explores a central issue in
artificial intelligence, cognitive science, and artificial life: how to
design information structures and processes that create and adapt intelligent
agents through evolution and learning. The book is organized around four
topics: (1) the power of evolution to determine effective solutions to
complex tasks; (2) mechanisms to make evolutionary design scalable; (3) the
use of evolutionary search in conjunction with local learning algorithms; and
(4) the extension of evolutionary search in novel directions."
Mukesh Patel is Vice President of Applied Solutions Ltd. and
Visiting Lecturer at the Nirma Institute of Technology, Ahmedabad, India.
Vasant Honavar is Associate Professor of Computer Science, Bioinformatics and
Computational Biology, and Neuroscience, and Director of the Artificial
Intelligence Laboratory, all at Iowa State University. Karthik Balakrishnan
leads the Decision Analytics Group at Obongo Inc. in California.
Hans-Paul Schwefel, Evolution and Optimum Seeking, John Wiley,
1995.
Moshe Sipper, Machine Nature: The Coming Age of
Bio-Inspired Computing, McGraw-Hill, 244 pp., July 2002. ISBN:
0-071-38704-8
From the publisher: "An enthralling look at how computer
scientists have crossed the line between machines and living
organisms. Sipper takes readers on a thrilling journey to the terra
nova of computing, to provide a compelling look at cutting-edge
computers, robots, and machines now and in the decades ahead."
Moshe Sipper is an Associate Professor in the Department of
Computer Science, Ben-Gurion University, Isreal, and a Visiting
Professor in the Logic Systems Laboratory at the Swiss Federal
Institute of Technology in Lausanne, Switzerland.
Frank Schweizer, Brownian Agents and Active Particles: Collective
Dynamics in the Natural and Social Sciences, with a Foreward by J. Doyne
Farmer, Springer, Berlin, 420pp., 2003. ISBN: 3-540-43938-2.
From the publisher: "By developing the genuine idea of Brownian
agents, the author combines concepts from informatics, such as multiagent
systems, with approaches of statistical many-particle physics. This way, an
efficient method for computer simulations of complex systems is developed
which is also accessible to analytical investigations and quantitative
predictions. The book demonstrates that Brownian agent models can be
successfully applied in many different contexts, ranging from physicochemical
pattern formation, to active motion and swarming in biological systems, to
self-assembling of networks, evolutionary optimization, urban growth,
economic agglomeration and even social systems."
Frank Schweitzer is with the Institute for Physics, Humboldt
University Berlin.
Rik K. Belew and Michael D. Vose (eds.), Foundations of Genetic Algorithms
4, Morgan Kaufmann, 1997.
L. E. Davis, ed., Handbook of Genetic Algorithms, Van Nostrand
Reinhold, N.Y., 1991.
Kenneth A. De Jong, "An Analysis of the Behaviour of a Class of Genetic
Adaptive Systems," Doctoral Thesis, Department of Computer and Communication
Sciences, University of Michigan, Ann Arbor, MI, 1975.
Robert E. Dorsey and W. J. Mayer, "Genetic Algorithms for Estimation
Problems with Multiple Optima, Nondifferentiability, and Other
Irregular Features," Journal of Business and Economic
Statistics 13 (1995), 53-66.
Stephanie Forrest, "Genetic Algorithms: Principles of Natural Selection
Applied to Computation," Science, Vol. 261 (August 1993),
pp. 872-878.
[A short and clearly-written introduction to GAs.]
Stephanie Forrest, ed., Emergent Computation: Self-Organizing,
Collective, and Cooperative Phenomena in Natural and Artificial
Computing Networks, The MIT Press, Cambridge, 1991.
[Special issue of Physica D.]
David Goldberg, Genetic Algorithms in Search, Optimization, and
Machine Learning, Addison-Wesley, Reading, 1989.
[A textbook on the theory, operation, and application of GAs.]
John Greffenstette, "The Evolution of Strategies for Multiagent
Environments," Adaptive Behavior 1 (1992), pp. 65-90.
W. Daniel Hillis, "Co-Evolving Parasites Improve Simulated Evolution
as an Optimization Procedure," pp. 313-324 in Artificial Life
II, ed. by Christopher Langton, Charles Taylor, J. Doyne Farmer, and
Steen Rasmussen, Addison-Wesley, Redwood City, CA, 1992.
John H. Holland, Adaptation in Natural and Artificial Systems:
An Introductory Analysis with Applications to Biology, Control, and
Artificial Intelligence, MIT Press/Bradford Books, Cambridge,
1992 (2nd edition).
John H. Holland, "Genetic Algorithms," Scientific
American 260 (July 1992), 44-51.
J. H. Holland, K. J. Holyoak, R. E. Nisbett, P.R. Thagard,
Induction, MIT Press, Cambridge, MA, 1986.
Zbigniew Michalewicz, Genetic Algorithms + Data Structures = Evolution
Programs, Springer, 2nd Edition, 1994.
Melanie Mitchell, An Introduction to Genetic Algorithms, MIT Press,
Cambridge, MA, 1996.
Covers terminology, GAs in machine learning and scientific models,
alternative approaches, implementation, and open questions.
Michael D. Vose, The Simple Genetic Algorithm: Foundations and
Theory, Bradford Books, December 1999, ISBN: 0-262-22058-X.
From Amazon.com: "Computer scientist Michael D. Vose takes a rigorous
look at The Simple Genetic Algorithm and shows the state of our
knowledge in a book appropriate for advanced undergraduates, graduate
students and professionals. Vose has decided to approach his subject as a
mathematical object, keeping his discussion to a minimum and relying on
mathematical demonstrations of what has been proven about this powerful
genetic search. This approach maximizes the book's utility for its scope of
readers; since each chapter builds on the material before, it makes a good
teaching tool, but it is still a useful reference as the indexing helps the
professional find proofs quickly."
Michael D. Vose is Associate Professor in the Department of Computer
Science at the University of Tennessee in Knoxville.
K. Kinnear, Jr. (ed.), Advances in Genetic Programming, MIT
Press, Cambridge, MA, 1994.
Discusses techniques for improving the
power of GP, public domain code available for GP (including C/C++ in
addition to LISP), and general internet GP resources.
John R. Koza, Genetic Programming: On the Programming of Computers by
Means of Natural Selection, MIT Press, Cambridge, 1992.
Genetically breeding populations of computer programs to solve
problems.
John R. Koza, "Genetic Evolution and Co-Evolution of Computer Programs," pp.
603-629 in Artificial Life II, edited by Christopher Langton, Charles
Taylor, Doyne Farmer, and Steen Rasmussen, Addison-Wesley, California, 1992.
John R. Koza, Genetic Programming II: Automatic Discovery of Reusable
Programs, MIT Press, Cambridge, MA, 1994.
See also J. Koza's Genetic Programming II Video: The
Next Generation, a 60-minute video that offers visual
representations of the applications of genetic programming described
in the book.
John R. Koza, Forrest H. Bennet III, Forrest H. Bennett, David Andre, and
Martin A. Keane, Genetic Programming III: Darwinian Invention and Problem
Solving, Morgan Kaufmann Publishers, March 1999, 1184 pp., ISBN
1-55-860543-6.
From the publisher: "Genetic programming is a method for getting a
computer to solve a problem by telling it what needs to be done instead of
how to do it. The authors present genetically evolved solutions to dozens of
problems of design, optimal control, classification, system identification,
function learning, and computational molecular biology. Among the solutions
are 14 competitive with human-produced results, including 10 rediscoveries
of previously patented inventions."
John R. Koza, Martin A. Keane, Matthew J. Streeter, William Nydlowec,
Jessen Yu, and Guido Lanza, Genetic Programming IV: Routine
Human-Competitive Machine Intelligence, Kluwer Academic Publishers,
Dordrecht, the Netherlands, 2004. ISBN: 1-402-07446-8.
From a book jacket comment by John H. Holland: "The research
reported in this book is a tour de force. For the first time since the idea
was bandied about in the 1940s and the early 1950s, we have a set of examples
of human-competitive automatic programming. These examples include the
automated re-creation of 21 previously patented inventions and the creation
of 2 patentable new inventions."
W. B. Langdon, Genetic Programming and Data Structures: Genetic
Programming + Data Structure = Automatic Programming!, Kluwer Academic
Publishers, 1998, 292 pp., ISBN 0-7923-8135-1.
From the publisher: "Computers that `program themselves' has long
been an aim of computer scientists. ... While (functions automatically
created by genetic programming) can be of great use, they contain no memory
and relatively little work has addressed automatic creation of program code
including stored data. (This book) shows how abstract data types (stacks,
queues and lists) can be evolved using genetic programming, and demonstrates
how genetic programming can evolve general programs which solve the nested
brackets problem, recognize a Dyck context free language, and implement a
simple four function calculator. In these cases, an appropriate data
structure is beneficial compared to simple indexed memory. This book also
includes a survey of genetic programming, with a critical review of
experiments with evolving memory..."
Lee Spector, William B. Langdon, Una-May O'Reilly, and Peter J. Angeline
(Eds.), Advances in Genetic Programming, Volume 3, MIT Press, 500
pages, August 1999, ISBN: 0262194236.
From the publisher: "Genetic programming is a form of evolutionary
computation that evolves programs and program-like executable structures for
reliable time- and cost-effective applications. It does this by breeding
programs over many generations, using the principles of natural selection,
sexual recombination, and mutation. This third volume of Advances in
Genetic Programming highlights many of the recent technical advances
in this increasingly popular field."
Lee Spector is Associate Professor of Computer Science, MacArthur
Chair, at Hampshire College. William B. Langdon is a Scientific Researcher
at the Centrum voor Wiskunde en Informatica. Una-May O'Reilly is
Postdoctoral Associate in the Artificial Intelligence Laboratory at the
Massachusetts Institute of Technology. Peter J. Angeline is Senior Staff
Scientist at Natural Selection, Inc.
2.D Evolutionary Programming and Evolution Strategies
Thomas Baeck and Hans-Paul Schwefel, "An Overview of Evolutionary
Algorithms for Parameter Optimization," Evolutionary
Computation 1 (1) 1993, pp. 1-23.
R. Manner and B. Manderick, eds., Parallel Problem
Solving From Nature, Elsevier Science Publishers, Amsterdam,
1992.
John R. McDonnell, Robert G. Reynolds, and David B. Fogel, Evolutionary
Programming IV, Proceedings of the Fourth Annual Conference on
Evolutionary Programming, MIT Press, Cambridge, 1995.
Hans-Paul Schwefel, Numerical Optimization of Computer Models, Wiley,
Chichester, 1981.
J. A. Anderson and E. Rosenfield (eds.), Talking Nets: An Oral History of
Neurocomputing, MIT Press, 1998, 0-262-01167-0.
From the book blurb:
"Since World War II, a group of scientists has been attempting to understand
the human nervous system and to build computer systems that emulate the
brain's abilities. ... In this collection of interviews, those who helped to
shape the field share their childhood memories, their influences, how they
became interested neural networks, and what they see as its future."
J. A. Anderson, A. Pellionisz, and E. Rosenfeld, eds.,
Neurocomputing 2: Directions for Research, MIT Press, Cambridge,
1990.
Sequel to the famous earlier volume, Neurocomputing:
Foundations of Research, edited by Anderson and E. Rosenfield.
Michael Arbib, ed., The Handbook of Brain Theory and Neural Networks,
MIT Press, Cambridge, MA, 1995.
Discusses progress
made in recent years in answering two related questions: How does
the brain work? and How can we build intelligent machines?
W. Aspray and A. W. Burks, Papers of John von Neumann on
Computing and Computer Theory, The MIT Press, Cambridge, 1987.
M. Brown and C. Harris, Neuro-Fuzzy Adaptive Modelling and
Control, Prentice-Hall, N.Y., 1994.
Maureen Caudill and Charles Butler, Naturally Intelligent
Systems, MIT Press, Massachusetts, 1991.
A comprehensive and
relatively nontechnical introduction to artificial neural networks.
Judith E. Dayhoff, Neural Network Architectures: An
Introduction, Van Nostrand Reinhold, New York, 1990.
Laurene Fausett, Fundamentals of Neural Networks,
Prentice-Hall, 1994, ISBN 0-13-334186-0.
James Freeman and David Skapura, Neural Networks,
Addison-Wesley, 1991, ISBN 0-201-51376-5.
S. Grossberg, The Adaptive Brain (in two volumes),
North-Holland, 1987.
R. Hecht-Nielsen, Neurocomputing, Addison Wesley, 1990.
John A. Hertz, Anders S. Krogh, and Richard G. Palmer,
Introduction to the Theory of Neural Computation, Santa Fe
Institute Studies in the Sciences of Complexity, Addison-Wesley,
1991. [Motivated by problems and methods in statistical physics.]
G. E. Hinton, "How Neural Nets Learn from Experience,"
Scientific American Vol. 267, No. 3 (1992), pp. 144-151.
G. E. Hinton, "Connectionist Learning Procedures," Artificial
Intelligence, Vol. 40 (1989), pp. 185-235.
V. Honavar
and L. Uhr (eds.), Artificial Intelligence and
Neural Networks: Steps Toward Principled Integration, Academic
Press, N.Y., 1994.
Vojislav Kecman, Learning and Soft Computing: Support Vector
Machines, Neural Networks, and Fuzzy Logic Models, The MIT
Press, March 2001, 608 pp., ISBN: 0-262-11255-8.
From the publisher: "This textbook provides a thorough
introduction to the field of learning from experimental data and
soft computing. Support vector machines (SVM) and neural networks
(NN) are the mathematical structures, or models, that underlie
learning, while fuzzy logic systems (FLS) enable us to embed
structured human knowledge into workable algorithms. This book
assumes that it is not only useful, but necessary, to treat SVM, NN,
and FLS as parts of a connected whole. Throughout, the theory and
algorithms are illustrated by practical examples, as well as by
problem sets and simulated experiments. The book also presents
three case studies: on NN-based control, financial time series
analysis, and computer graphics. A solutions manual and all of the
MATLAB programs needed for the simulated experiments are available."
Vojislav Kecman is with the Department of Mechanical
Engineering, University of Auckland, New Zealand.
K. Knight, "Connectionist Ideas and Algorithms," Communications
of the ACM, Vol. 33 (November 1990), pp. 59-74.
Teuvo J. Kohonen, Self-Organization and Associative Memory,
Springer-Verlag, N.Y., Third Edition, 1989.
Klaus Obermayer and Terrence J. Sejnowski (eds.), Self-Organizing Map
Formation, MIT Press, A Bradford Book, July 2001, 415 pages, ISBN:
0-262-65060-6.
From the publisher: "This book provides an overview of
self-organizing map formation, including recent developments.
Self-organizing maps form a branch of unsupervised learning, which is the
study of what can be determined about the statistical properties of input
data without explicit feedback from a teacher. The articles are drawn from
the journal Neural Computation."
Klaus Obermayer is Professor of Computer Science and Head of the
Neural Information Processing Group at the Technical University of Berlin.
Terrence J. Sejnowski is Head of the Department of Computational Neurobiology
at the Salk Institute of Biological Studies and Professor of Biology and the
University of California, San Diego.
Y. H. Pao, Adaptive Pattern Recognition and Neural
Networks, Addison-Wesley, 1989. [Ties together classical pattern
recognition approaches with ANNs.]
Philip Picton, Neural Networks, St. Martin's Press, 195
pp., Second Edition, June 2001, ISBN: 0-333-94899-8.
From the publisher: "This updated and revised second edition assumes
no prior knowledge and sets out to describe what neural networks are, what
they do, and how they do it. The main networks covered include ADALINE,
WISARD, the Hopfield Network, Bidirectional Associative Memory, the Boltzmann
machine, counter-propagation, ART networks, and Kohonen's self-organizing
maps. These networks are discussed by means of examples, giving the reader a
good overall knowledge of current developments in the field."
Philip Picton is a professor at the School of Technology and Design,
University College, Northampton.
Jose C. Pincipe, Neil R. Euliano, and W. Curt Lefebvre,
Neural and Adaptive Systems: Fundamentals Through
Simulations, John Wiley and Sons, 672 pp., November 1999, ISBN:
0-471-35167-9 (book and CD-ROM edition).
From the publisher: "This one-of-a-kind interactive book and CD-ROM
will help you develop a better understanding of the behavior of adaptive
systems. Developed as part of a project aimed at innovating the teaching of
adaptive systems in science and engineering, it unifies the concepts of
neural networks and adaptive filters into a common framework. It begins by
explaining the fundamentals of adaptive linear regression and builds on these
concepts to explore pattern classification, function approximation, feature
extraction and time-series modeling/prediction. The text is integrated with
the industry standard neural network/adaptive system simulator
NeuroSolutions. This allows the authors to demonstrate and reinforce key
concepts using over 200 interactive examples. Each of these examples is
`live,' allowing the user to change parameters and experiment first-hand with
real-world adaptive systems. This creates a powerful environment for
learning through both visualization and experimentation."
David E. Rumelhart, G. E. Hinton, and R. J. Williams, "Learning
Representations by Back-Propagating Errors," Nature, Vol. 323
(October 1986), pp. 533-536.
David Rumelhart and J. McClelland, eds., Parallel Distributed
Processing: Explorations in the Microstructure of Cognition (in
three volumes), MIT Press, Cambridge, 1986.
P. Wasserman, Neural Networks, 1989, ISBN 0-442-20743-3.
Per Bak and K. Chen, "Self-Organized Criticality," Scientific
American (January 1991), pp. 46-53.
Carlos A. Coello Coello, Dave A. Van Veldhuizen, and Gary B. Lamont,
Evolutionary Algorithms for Solving Multi-Objective Problems, Volume
5, Genetic Algorithms and Evolutionary Computation Book Series, Kluwer
Academic Publishers, May 2002. ISBN: 0-306-46762-3.
This book contains a comprehensive review of the field known as
evolutionary multiobjective optimization. It covers algorithms, theory,
multicriteria decisionmaking, test suites, metrics, applications, and
parallel techniques.
David Corne, Marco Dorigo, and Fred Glover (eds.), New Ideas in
Optimization, McGraw-Hill,
1999, £34.99. ISBN 0-07-709506-5
From the publisher: "New Ideas in Optimization
is suitable for advanced undergraduate and masters course modules in Heuristic
Techniques, Optimization, Evolutionary Algorithms and Advance Problem Solving
taught worldwide as part of Computer Science, AI, and Intelligent Systems
degrees. ... (This is) the first book to introduce, in a way suitable for
advanced undergraduates and above, the very latest collection of optimization
techniques in computer science and artificial intelligence. (E)ach of the
new techniques is introduced by either its inventor or a pioneer in its
applications."
Topics include: ant colony optimization; differential evolution;
immune system methods; memetic algorithms; scatter search and path relinking;
coevolutionary algorithms; cultural algorithms; particle swarm systems;
parallel distributed genetic programming; and probabilistic incremental
program evolution.
David Corne is with the University of Reading, UK. Marco
Dorigo is a research associate with the Belgian FNRS at the Université
Libre de Bruxelles. Fred Glover is the MediaOne Chaired Professor at the
University of Colorado, USA.
Robert L. Devaney and Linda Keen, eds., Chaos and Fractals,
Proceedings of the Symposia in Applied Mathematics, Volume 39,
American Mathematical Society, 1989.
Christodoulos A. Floudas and Panos M. Pardalos (eds.),
Encyclopedia of Optimization, Volumes 1 through 6, Kluwer
Academic Publishers, May 2001, 3200 pp., ISBN 0-792-36932-7.
From the publisher: "The Encyclopedia of Optimization
aims at serving as an important reference for all parts of
optimization. It is directed to a diverse audience of students,
scientists, engineers and in general to any decision maker and
problem solver in academia, business, industry, and government who
is concerned with aspects of optimization theory, algorithms, and
applications."
Christodoulos A. Floudas is with Princeton University and
Panos M. Pardalos is with the Department of Industrial and Systems
Engineering at the University of Florida, Gainesville.
David B. Fogel, Blondie24: Playing at the Edge of AI, Morgan
Kaufmann Publishers, 424 pp., September 2001. ISBN: 1-558-60783-8.
From an Amazon.com editorial review by Rob Lightner: "What must it do
to the human male ego to find out that the young woman who just handily won an
online game of checkers is actually a sleek piece of software with no real
understanding of the game's rules? Evolutionary programmers David B. Fogel
and Kumar Chellapilla learned this and many other lessons in their quest to
build a problem-solver divorced from human expertise. Fogel's book...
captures their spirit of good-natured questioning of the received wisdom of
traditional checkers playing and AI research. The writing is surprisingly
engaging, coming from a software researcher: even readers with little
interest in checkers will follow Fogel's many game analyses with rising
interest as his neural networks increase in prowess. Even the scientist, he
includes a laundry list of fairly harsh critiques of his own work - with
rebuttals - in an appendix. Devotees of cutting-edge AI, online psychology,
or tournament-level checkers will find plenty of interest in the exploits of
Blondie24."
Dr. David B. Fogel is the CEO of Natural Selection, Inc.
(La Jolla, California), a company which applies evolutionary computation to a
wide variety of real-world problems. He is also the founder of the
Evolutionary Programming Society and past-editor of the IEEE Transactions
on Evolutionary Computation.
Richard J. Gaylord and K. Nishidate, Modeling Nature: Cellular Automata
Simulations with Mathematics, Springer-Verlag, 1996, ISBN
0-387-94620-9.
James Gleick,
Chaos: Making a New Science, Viking Press, 1987.
A relatively
nontechnical discussion of complexity theory for the interested
non-specialist, a fun and highly readable account still useful as an
introduction to the field.
David Griffeath and Cristopher Moore, New Constructions in
Cellular Automata, SFI Studies in the Sciences of Complexity,
Oxford University Press, May 2002, ISBN: 0-195-13718-3 (paperback).
From the authors: "This book not only discusses cellular automata
(CA) as accoutrements for simulation, but also the actual building of devices
within cellular automata. CA are widely used tools for simulation in
physics, ecology, mathematics, and other fields. But they are also digital
`toy universes' worthy of study in their own right, with their own laws of
physics and behavior. In studying CA for their own sake, we must look at
constructive methods, that is, the practice of actually building devices in a
given CA that store and process information, replicate and propagate
themselves, and interact with other devices in a complex way. By building
such machines, we learn what the CA's dynamics are capable of, and build an
intuition about how to `engineer' the machine we want. We can also address
fundamental questions, such as whether universal computation or even `living'
things that reproduce and evolve can exist in the CA's digital world, and
perhaps, how these things came to be in our own universe."
David Griffeath is a Professor of Mathematics at the University of
Wisconsin, Madison. He is also the creator of the award-winning web site,
the Primordial Soup Kitchen, and a member of the External Faculty of the
Santa Fe Institute. Cristopher Moore holds a joint appointment in the
Computer Science Department and the Department of Physics and Astronomy at
the University of New Mexico, and is a member of the External Faculty of the
Santa Fe Institute.
W. Daniel Hillis, "The Connection Machine," Scientific American
255 (6), 1987.
W. Daniel Hillis, "Massively Parallel Computing," Daedalus,
Winter, 121 (1) 1992, pp. 1-29.
Feng-hsiung Hsu, Behind Deep Blue, Princeton University
Press, 320pp., 2002, ISBN: 0-691-09065-3.
From the publisher: "Written by the man who started the
adventure, (this book) reveals the inside story of what happened
behind the scenes at the two historic Deep Blue vs. Kasparov
matches. This is also the story behind the quest to create the
mother of all chess machines. The book unveils how a modest student
project eventually produced a multi-million dollar supercomputer,
from the development of the scientific ideas through technical
setbacks, rivalry in the race to develop the ultimate chess machine,
and wild controversies to the final triumph over the world's
greatest human player."
Feng-hsiung Hsu is the founding father of the Deep Blue project. He
is currently a research scientist at the Western Research Lab of Compaq
Computer, Inc.
Christian Jacob, Illustrating Evolutionary Computation with
Mathematica, Morgan Kaufmann Publishers, 616 pp., February 2001.
ISBN: 1-558-60637-8.
From an amazon.com editorial review by Rob Lightner:
"Living organisms manage to solve all kinds of deviously complex
problems with a natural simplicity that leaves programmers
speechless. Incorporating techniques based on principles elaborated
by Darwin and his intellectual descendents, a new generation of
hackers has tackled hairy challenges with surprising success.
Christian Jacob introduces interested programmers and scientists
to these tools... The basics of biological evolution through mutation
and adaptation are covered quickly before they are adapted
themselves to the purposes of computer-aided problem solving. Jacob
then explores the fundamentals of evolutionary computing through
well-illustrated examples and a good balance of text, formulae, and
code. Genetic algorithms, evolutionary strategies, and finite state
automata each get their share of attention and integration with
Evolvica, Jacob's Mathematica-based genetic programming system. The
system and Web enhancements to the book are available through the
University of Calgary's site and are essential for getting the most
from the text. The last few chapters cover advanced applications
like the classic `hungry ants' programs, cellular automata, and
artificial plant evolution, suggesting further possibilities for this
programming frontier."
James Kennedy, Russell C. Eberhart, and Yuhui Shi, Swarm
Intelligence, Morgan Kauffmann Publishers, 510 pp., March 2001,
ISBN: 1-558-60595-9.
From Book News, Inc. (Portland, OR): "Particle swarm optimization
(PSO) is a new kind of social intelligence model. This interdisciplinary
work places particle swarms within the larger context of intelligent adaptive
behavior and evolutionary computation, drawing on findings in
social-psychological and engineering research to derive a set of optimization
algorithms that shed light on human information processing and provide tools
for numerical and qualitative optimization. (The book should be) of interest
to researchers and graduate students in cognitive, social, and computer
science."
Daniel Mange and Marco Tomassini (eds.), Bio-Inspired Computing
Machines, Presses Polytechniques et Universitaires Romandes,
1998, 384 pp., CHF 79. ISBN 2-88074-371-0
From the publisher: "This volume, written by experts in the field,
gives a modern, rigorous and unified presentation of the application of
biological concepts to the design of novel computing machines and algorithms.
... This book is unique for the following reasons. It follows a unified
approach to bio-inspiration based on the so-called POE model: phylogeny
(evolution of species), ontogeny (development of individual organisms), and
epigenesis (life-time learning). It is largely self-contained with an
introduction to both biological mechanisms (POE) and digital hardware
(digital systems, cellular automata). It is mainly applied to computer
hardware design. ... (The book is aimed at) undergraduate and graduate
students, researchers, engineers, computer scientists, and communication
specialists."
Daniel Mange is Professor at the Swiss Federal Institute of
Technology, and Marco Tomassini is Professor at the University of Lausanne, Switzerland.
Manfred Opper and David Saad, Advanced Mean Field Methods, MIT
Press, March 2001, 300 pp., ISBN 0-262-15054-9.
From the publisher: "A major problem in modern
probabilistic modeling is the huge computational complexity involved
in typical calculations with multivariate probability distributions
when the number of random variables is large. Because exact
computations are infeasible in such cases and Monte Carlo sampling
techniques may reach their limits, there is a need for methods that
allow for efficient approximate computations. One of the simplest
approximations is based on the mean field method, which has a long
history in statistical physics. ... Bringing together ideas and
techniques from ... diverse disciplines, this book covers the
theoretical foundations of advanced mean field methods, explores the
relation between the different approaches, examines the quality of
the approximation obtained, and demonstrates their application to
various areas of probabilistic modeling."
Manfred Opper is a Reader and David Saad is Professor, the
Neural Computing Research Group, School of Engineering and Applied
Science, Aston University, UK.
Enrique Ruspini, Piero Bonissone, and Witold Pedrycz (eds.),
Handbook of Fuzzy Computation, Institute of Physics
Publishing, 1998, ISBN 0-75030427-8.
From the publisher: "Fuzzy computation encompasses the
application of the theories of fuzzy sets and fuzzy logic to the
solution of information processing and systems-analysis problems.
Initially conceived as a methodology for the representation and
manipulation of imprecise and vague information, fuzzy computation
has found wide utilization in problems that fall well beyond its
originally intended scope of application. ... The Handbook of
Fuzzy Computation is a major reference work intended to serve
both as a repository of information about fundamental aspects of the
field and as a stepping stone into detailed explorations into the
myriad applications of fuzzy-logic techniques and methods."
Ruspini is with SRI International, U.S.A., Bonissone is with
the GE Corporation, U.S.A., and Pedryca is with the University of
Manitoba, Canada.
Moshe Sipper, Evolution of Parallel Cellular Machines: The
Cellular Programming Approach, Springer-Verlag, 1997, ISBN:
3-540-62613-1.
Examines the behavior of parallel cellular machines, the complex behavior
they exhibit, and the appliation of artificial evolution to such systems.
V. S. Subrahmanian, Piero Bonatti, Juergen Dix, Thomas Eiter, Sarit
Kraus, Fatma Ozcan, and Robert Ross, Heterogeneous Agent Systems, MIT
Press, July 2000, 640 pages, ISBN (cloth): 0-262-19436-8.
From the publisher: "Software agents are the latest advance in the
trend toward smaller, modular pieces of code, where each module performs a
well-defined, focused task or set of tasks. Programmed to interact with and
provide services to other agents, including humans, software agents act
autonomously with prescribed backgrounds, beliefs, and operations. Systems of
agents can access and manipulate heterogeneously stored data such as that
found on the Internet. After a discussion of the theory of software agents,
this book presents IMPACT (Interactive Maryland Platform for Agents
Collaborating Together), an experimental agent infrastructure that translates
formal theories of agency into a functional multiagent system that can extend
legacy software code and application-specific or legacy data structures. The
book describes three sample applications: a store, a self-correcting
auto-pilot, and a supply chain."
Paul P. Wang (ed.), Computing with Words, John Wiley and
Sons, Inc., New York, 748 pp., April 2001. ISBN: 0-471-35374-4.
From the publisher: "Researchers have dubbed the twenty-first
century the `century of semantics,' and this timely volume is a response to
the need and demand for a book on the evolving topic of computing with words.
The chapters are written by leading reseachers within the fuzzy research
community and provide a complete overview of theory, current technology, and
potential applications. A larger view of semiotics and intelligence systems
as they relate to computing with words is also presented. ... Researchers in
fuzzy logic, information science, and linguistic computation will find (this
book) an essential source on information."
Paul P. Wang is Professor of Electrical and Computer Engineering at
the Pratt School of Engineering, Duke University, Durham, NC.
Stephen Wolfram, A New Kind of Science, Wolfram Media, Inc., 1192
pp., May 2002. ISBN: 1-579-55008-8.
From the publisher: "This long-awaited work from one of the world's
most respected scientists presents a series of dramatic discoveries never
before made public. Starting from a collection of simple computer
experiments - illustrated in the book by striking computer graphics -
Wolfram shows how their unexpected results force a whole new way of looking
at our universe. Wolfram uses his approach to tackle a remarkable array of
fundamental problems in science: from the origin of the Second Law of
thermodynamics, to the development of complexity in biology, the computational
limitations of mathematics, the possibility of a truly fundamental theory
of physics, and the interplay between free will and determinism."
Dr. Stephen Wolfram, creator of Mathematica in 1986, is the founder
and CEO of Wolfram Research, Inc., a software company.
tesfatsi at iastate.edu
IMPORTANT NOTICE:
2. Evolutionary Computation