Evolutionary Neural Networks for Value Ordering in Constraint SatisfactionProblems

A new method for developing good value-ordering strategies in constraint satisfaction search is presented. Using an evolutionary technique called SANE, in which individual neurons evolve to cooperate and form a neural network, problem-specific knowledge can be discovered that results in better value-ordering decisions than those based on problem-general heuristics. A neural network was evolved in a chronological backtrack search to decide the ordering of cars in a resource-limited assembly line. The network required 1/30 of the backtracks of random ordering and 1/3 of the backtracks of the maximization of future options heuristic. The SANE approach should extend well to other domains where heuristic information is either difficult to discover or problem-specific.

[1]  Norman Sadeh,et al.  Look-ahead techniques for micro-opportunistic job shop scheduling , 1992 .

[2]  Risto Miikkulainen,et al.  Evolving Neural Networks to Focus Minimax Search , 1994, AAAI.

[3]  Edward M. Reingold,et al.  Backtrack programming techniques , 1975, CACM.

[4]  Rina Dechter,et al.  Network-Based Heuristics for Constraint-Satisfaction Problems , 1987, Artif. Intell..

[5]  David R. Jefferson,et al.  Selection in Massively Parallel Genetic Algorithms , 1991, ICGA.

[6]  Yuval Davidor,et al.  A Naturally Occurring Niche and Species Phenomenon: The Model and First Results , 1991, ICGA.

[7]  Rina Dechter,et al.  Enhancement Schemes for Constraint Processing: Backjumping, Learning, and Cutset Decomposition , 1990, Artif. Intell..

[8]  Alan K. Mackworth Consistency in Networks of Relations , 1977, Artif. Intell..

[9]  Robert M. Haralick,et al.  Increasing Tree Search Efficiency for Constraint Satisfaction Problems , 1979, Artif. Intell..

[10]  Pascal Van Hentenryck,et al.  Constraint Satisfaction Using Constraint Logic Programming , 1992, Artif. Intell..

[11]  Paul Walton Purdom,et al.  Search Rearrangement Backtracking and Polynomial Average Time , 1983, Artif. Intell..

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

[13]  Gerald J. Sussman,et al.  Forward Reasoning and Dependency-Directed Backtracking in a System for Computer-Aided Circuit Analysis , 1976, Artif. Intell..

[14]  Vipin Kumar,et al.  Algorithms for Constraint-Satisfaction Problems: A Survey , 1992, AI Mag..

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

[16]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[17]  Risto Miikkulainen,et al.  Evolving Complex Othello Strategies Using Marker-Based Genetic Encoding ofNeural Networks , 1993 .

[18]  A. Barto,et al.  Learning and Sequential Decision Making , 1989 .

[19]  L. Darrell Whitley,et al.  Genetic algorithms and neural networks: optimizing connections and connectivity , 1990, Parallel Comput..