Genetic programming and emergent intelligence

Angeline 23 Fogel, D. B (1993). Using evolutionary programming to create neural networks that are capable of playing Tic-Tac-Toe. (1992). Evolution as a theme in artificial life: The genesys/tracker system. In Artificial Life II, C. Angeline 22 4.6 Conclusion Artificial intelligence has made great strides in computational problem solving using explicitly represented knowledge extracted from the task. If we continue to use explicitly represented knowledge exclusively for computational problem solving, we may never computationally accomplish a level of problem solving performance equal to humans. Emergent intelligence de-emphasizes the role of explicit knowledge and encourages the development of solutions that incorporate the task description as a component of the problem solver. This allows the constraints of the task to be represented more naturally and permits only pertinent task specific knowledge to emerge in the course of solving the problem.

[1]  James R. Levenick.  Inserting Introns Improves Genetic Algorithm Success Rate: Taking a Cue from Biology , 1991, ICGA.

[2]  Peter J. Angeline,et al.  Competitive Environments Evolve Better Solutions for Complex Tasks , 1993, ICGA.

[3]  A. Newell.  Unified Theories of Cognition , 1990 .

[4]  John H. Holland,et al.  Adaptation in natural and artificial systems , 1975 .

[5]  Nils J. Nilsson,et al.  Artificial Intelligence , 1974, IFIP Congress.

[6]  Stephanie Forrest,et al.  Emergent computation: self-organizing, collective, and cooperative phenomena in natural and artificial computing networks , 1990 .

[7]  J. Pollack,et al.  Coevolving High-Level Representations , 1993 .

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

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

[10]  Thomas S. Ray,et al.  An Approach to the Synthesis of Life , 1991 .

[11]  D. B. Fogel,et al.  Using evolutionary programing to create neural networks that are capable of playing tic-tac-toe , 1993, IEEE International Conference on Neural Networks.

[12]  Melanie Mitchell,et al.  Relative Building-Block Fitness and the Building Block Hypothesis , 1992, FOGA.

[13]  Lawrence J. Fogel,et al.  Artificial Intelligence through Simulated Evolution , 1966 .

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

[15]  Thomas Bäck,et al.  A Survey of Evolution Strategies , 1991, ICGA.

[16]  Allen Newell,et al.  The Knowledge Level , 1989, Artif. Intell..

[17]  K. Dejong,et al.  An analysis of the behavior of a class of genetic adaptive systems , 1975 .

[18]  Peter J. Angeline,et al.  An evolutionary algorithm that constructs recurrent neural networks , 1994, IEEE Trans. Neural Networks.

[19]  Kalyanmoy Deb,et al.  Messy Genetic Algorithms: Motivation, Analysis, and First Results , 1989, Complex Syst..

[20]  Peter J. Angeline,et al.  Evolutionary Module Acquisition , 1993 .

[21]  Zbigniew Michalewicz,et al.  A Hierarchy of Evolution Programs: An Experimental Study , 1993, Evolutionary Computation.

[22]  David E. Goldberg,et al.  Zen and the Art of Genetic Algorithms , 1989, ICGA.

[23]  David B. Fogel,et al.  Evolving artificial intelligence , 1992 .