Emergent computation: self-organizing, collective, and cooperative phenomena in natural and artificial computing networks

Researchers in several fields are exploring computational systems in which interesting global behavior emerges from local interactions among component parts - an approach called emergent computation. In these systems, interactions among simultaneous computations are exploited to improve efficiency, increase flexibility, or provide more realistic models of natural phenomena. These 31 essays define and explore the concept of emergent computation in such areas as artificial networks, adaptive systems, classifier systems, connectionist learning, other learning, and biological networks to determine what properties are required of the supporting architectures that generate them.Many of the essays share the themes of design (how to construct such systems), the importance of preexisting structure to learning and the role of parallelism, and the tension between cooperative and competitive models of interaction. In the introduction, Stephanie Forrest presents several detailed examples of the kinds of problems emergent computation can address. These include showing how emergent computation can lead to efficiency improvements in parallel processing, establishing the connection between emergent computation and nonlinear systems, and comparing two search techniques to show how the emergent-computational approach to a problem differs from other more conventional approaches.

[1]  Stephen M. Omohundro,et al.  Geometric learning algorithms , 1990 .

[2]  Stevan Harnad,et al.  Symbol grounding problem , 1990, Scholarpedia.

[3]  Steen Rasmussen,et al.  Computational connectionism within neurons: a model of cytoskeletal automata subserving neural networks , 1990 .

[4]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[5]  G. Reeke,et al.  Selectionist models of perceptual and motor systems and implications for functionalist theories of brain function , 1990 .

[6]  Larry J. Eshelman,et al.  Using genetic search to exploit the emergent behavior of neural networks , 1990 .

[7]  I. Kanter,et al.  Synchronous or asynchronous parallel dynamics which is more efficient , 1990 .

[8]  Wolfgang Banzhaf,et al.  An energy function for specialization , 1990 .

[9]  John H. Miller,et al.  Emergent behavior in classifier systems , 1990 .

[10]  Steen Rasmussen,et al.  The coreworld: emergence and evolution of cooperative structures in a computational chemistry , 1990 .

[11]  Allen Newell,et al.  SOAR: An Architecture for General Intelligence , 1987, Artif. Intell..

[12]  Christopher G. Langton,et al.  Computation at the edge of chaos: Phase transitions and emergent computation , 1990 .

[13]  Quentin F. Stout,et al.  The complex behavior of simple machines , 1990 .

[14]  John H. Holland,et al.  Induction: Processes of Inference, Learning, and Discovery , 1987, IEEE Expert.

[15]  R. Axelrod.  An Evolutionary Approach to Norms , 1986, American Political Science Review.

[16]  J. H. Miller,et al.  Emergent behaviors of classifier systems , 1989 .

[17]  Stephen Wolfram,et al.  Universality and complexity in cellular automata , 1983 .

[18]  Daniele Montanari,et al.  Learning and bucket brigade dynamics in classifier systems , 1990 .

[19]  E. Lorenz.  Deterministic nonperiodic flow , 1963 .

[20]  Allen Newell,et al.  GPS, a program that simulates human thought , 1995 .

[21]  Robert Shaw.  Strange Attractors, Chaotic Behavior, and Information Flow , 1981 .

[22]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[23]  Christopher G. Langton,et al.  Studying artificial life with cellular automata , 1986 .

[24]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[25]  R. J. Nelson,et al.  Introduction to Automata , 1968 .

[26]  W. Daniel Hillis,et al.  Co-evolving parasites improve simulated evolution as an optimization procedure , 1990 .

[27]  Bernardo A. Huberman,et al.  The performance of cooperative processes , 1990 .

[28]  Herbert A. Simon,et al.  The Sciences of the Artificial , 1970 .

[29]  Melanie Mitchell,et al.  The emergence of understanding in a computer model of concepts analogy-making , 1990 .

[30]  Zurek,et al.  Algorithmic randomness and physical entropy. , 1989, Physical review. A, General physics.

[31]  Bill Baird,et al.  Bifurcation and category learning in network models of oscilating cortex , 1990 .

[32]  E. F. Codd,et al.  Cellular automata , 1968 .

[33]  Joseph E. Stoy,et al.  Denotational Semantics: The Scott-Strachey Approach to Programming Language Theory , 1981 .

[34]  John H. Holland,et al.  Concerning the emergence of tag-mediated lookahead in classifier systems , 1990 .

[35]  Grégoire Nicolis,et al.  Self-Organization in nonequilibrium systems , 1977 .

[36]  W. H. Zurek,et al.  Thermodynamic cost of computation, algorithmic complexity and the information metric , 1989, Nature.

[37]  P. Churchland.  On the nature of explanation: a PDP approach , 1990 .

[38]  Daniel R. Greening,et al.  Parallel simulated annealing techniques , 1990 .

[39]  Takashi Ikegami,et al.  Computer symbiosis-emergence of symbiotic behavior through evolution , 1990 .

[40]  Ralph M. Siegel,et al.  Non-linear dynamical system theory and primary visual cortical processing , 1990 .

[41]  Stewart W. Wilson.  Perceptron redux: emergence of structure , 1990 .

[42]  Stephen José Hanson,et al.  A stochastic version of the delta rule , 1990 .

[43]  G. Amdhal,et al.  Validity of the single processor approach to achieving large scale computing capabilities , 1967, AFIPS '67 (Spring).

[44]  J. Keeler.  A dynamical system view of cerebellar function , 1990 .

[45]  E. R. Flynn,et al.  Neuromagnetic studies of human vision: noninvasive characterization of functional neural architecture , 1990 .

[46]  Tad Hogg,et al.  Collective behavior of predictive agents , 1990 .

[47]  J. Doyne Farmer,et al.  A Rosetta stone for connectionism , 1990 .

[48]  Roy A. Maxion,et al.  Toward diagnosis as an emergent behavior in a network ecosystem , 1990 .

[49]  Stuart A. Kauffman,et al.  Requirements for evolvability in complex systems: orderly dynamics and frozen components , 1990 .

[50]  J. Palmore,et al.  Computer arithmetic, chaos and fractals , 1990 .