The linkage tree genetic algorithm
作者： Dirk Thierens
DOI: 10.1007/978-3-642-15844-5_27
关键词: Genetic algorithm 、 Hierarchical clustering 、 Combinatorics 、 Variation of information 、 Metric (mathematics) 、 Mathematics 、 Cluster analysis 、 Crossover 、 Linkage (mechanical) 、 Tree (data structure) 、 Algorithm
摘要: We introduce the Linkage Tree Genetic Algorithm (LTGA), a competent genetic algorithm that learns linkage between problem variables. The LTGA builds each generation tree using hierarchical clustering algorithm. To generate new offspring solutions, selects two parent solutions and traverses starting from root. At branching point, pair is recombined crossover mask defined by at particular node. competes with pair, continues traversing has most fit solution. Once entire traversed, best solution of current copied to next generation. In this paper we use normalized variation information metric as distance measure for process. Experimental results fully deceptive functions nearest neighbor NK-landscape problems tunable overlap show can solve these hard efficiently without knowing actual position linked variables on representation.
springer.com
acm.org 
sci-hub.st 参考文章(16)
Scalable Optimization via Probabilistic Modeling Springer Berlin Heidelberg. ,(2006) , 10.1007/978-3-540-34954-9
Martin Pelikan, Erick Cantú-Paz, Kumara Sastry, Scalable Optimization via Probabilistic Modeling: From Algorithms to Applications (Studies in Computational Intelligence) Springer-Verlag New York, Inc.. ,(2006)
Martin Pelikan, Kumara Sastry, Martin V. Butz, David E. Goldberg, Performance of evolutionary algorithms on random decomposable problems parallel problem solving from nature. pp. 788- 797 ,(2006) , 10.1007/11844297_80
Dirk Thierens, David E. Goldberg, Mixing in Genetic Algorithms international conference on genetic algorithms. pp. 38- 47 ,(1993)
Georges R. Harik, Fernando G. Lobo, Kumara Sastry, Linkage Learning via Probabilistic Modeling in the Extended Compact Genetic Algorithm (ECGA) Scalable Optimization via Probabilistic Modeling. pp. 39- 61 ,(2006) , 10.1007/978-3-540-34954-9_3
Kalyanmoy Deb, David E Goldberg, Illinois Genetic Algorithms Laboratory. Department of General Engineering. University of Illinois at Urbana Champaign, Analyzing Deception in Trap Functions foundations of genetic algorithms. ,vol. 2, pp. 93- 108 ,(1993) , 10.1016/B978-0-08-094832-4.50012-X
Linkage in evolutionary computation Springer. ,(2008) , 10.1007/978-3-540-85068-7
David E. Goldberg, The Design of Innovation: Lessons from and for Competent Genetic Algorithms ,(2002)
Martin Pelikan, Kumara Sastry, David E. Goldberg, Martin V. Butz, Mark Hauschild, Performance of evolutionary algorithms on NK landscapes with nearest neighbor interactions and tunable overlap Proceedings of the 11th Annual conference on Genetic and evolutionary computation - GECCO '09. pp. 851- 858 ,(2009) , 10.1145/1569901.1570018
A Kraskov, H Stögbauer, R. G Andrzejak, P Grassberger, Hierarchical clustering using mutual information EPL. ,vol. 70, pp. 278- 284 ,(2005) , 10.1209/EPL/I2004-10483-Y