论文信息 - Implicit Formae in Genetic Algorithms

Implicit Formae in Genetic Algorithms

This paper discusses the term implicit forma, which is useful for explaining the behaviour of genetic algorithms. Implicit formae are predicates over the chromosome space that are not strongly connected to the representation at hand but are capable of directing the search. After a short theoretical discussion, three examples are given for illustration, including the subset sum problem which is NP-complete.

Márk Jelasity | József Dombi

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

[2] Hillol Kargupta,et al. Signal-to-noise, Crosstalk, and Long Range Problem Difficulty in Genetic Algorithms , 1995, ICGA.

[3] Thomas Bäck,et al. An evolutionary approach to combinatorial optimization problems , 1994, CSC '94.

[4] Felicity A. W. George,et al. A Study in Set Recombination , 1993, ICGA.

[5] Patrick D. Surry,et al. Fitness Variance of Formae and Performance Prediction , 1994, FOGA.

[6] Martin Wattenberg,et al. Stochastic Hillclimbing as a Baseline Mathod for Evaluating Genetic Algorithms , 1995, NIPS.

[7] Nicholas J. Radcliffe,et al. Equivalence Class Analysis of Genetic Algorithms , 1991, Complex Syst..

[8] S. J. Flockton,et al. Modelling the behaviour of the genetic algorithm , 1995 .

[9] Nicholas J. Radcliffe,et al. Non-Linear Genetic Representations , 1992, PPSN.

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

[11] Michael D. Vose,et al. Generalizing the Notion of Schema in Genetic Algorithms , 1991, Artif. Intell..

[12] John H. Holland,et al. When will a Genetic Algorithm Outperform Hill Climbing , 1993, NIPS.