论文信息 - A self adaptive hybrid genetic algorithm

A self adaptive hybrid genetic algorithm

This paper presents a self-adaptive hybrid genetic algorithm (SAHGA) and compares its performance to a non-adaptive hybrid genetic algorithm (NAHGA) and the simple genetic algorithm (SGA) on two multi-modal test functions with complex geometry. The SAHGA is shown to be far more robust than the NAHGA, providing fast and reliable convergence across a broad range of parameter settings. For the most complex test function, the SAHGA required over 75% fewer function evaluations than the SGA to identify the optimal solution.

[1] J. Baldwin. A New Factor in Evolution , 1896, The American Naturalist.

[2] Geoffrey E. Hinton,et al. How Learning Can Guide Evolution , 1996, Complex Syst..

[3] R. French,et al. Genes, Phenes and the Baldwin Effect: Learning and Evolution in a Simulated Population , 1994 .

[4] L. Darrell Whitley,et al. Lamarckian Evolution, The Baldwin Effect and Function Optimization , 1994, PPSN.

[5] David E. Goldberg,et al. Optimizing Global-Local Search Hybrids , 1999, GECCO.

[6] M. C. Sinclair. Minimum cost wavelength-path routing and wavelength allocation using a genetic-algorithm/heuristic hybrid approach , 1999 .

[7] Mika Johnsson,et al. An adaptive hybrid genetic algorithm for the three-matching problem , 2000, IEEE Trans. Evol. Comput..

[8] Angelo M. Sabatini,et al. A hybrid genetic algorithm for estimating the optimal time scale of linear systems approximations using Laguerre models , 2000, IEEE Trans. Autom. Control..

[9] David E. Goldberg,et al. Designing a competent simple genetic algorithm for search and optimization , 2000 .