论文信息 - gLINC: identifying composability using group perturbation

gLINC: identifying composability using group perturbation

We present two novel perturbation-based linkage learning algorithms that extend LINC [5]; a version of LINC optimised for decomposition tasks (oLINC) and a hierarchical version of oLINC (gLINC). We show how gLINC decomposes a fitness landscape significantly faster than both LINC and oLINC.We present details of LINC, oLINC and gLINC, an empirical comparison of their speed, accuracy and sensitivity to population size on a concatenated trap function, and a discussion of their complexity and correctness.

Christopher D. Clack | David Jonathan Coffin | C. Clack | D. Coffin

[1] J. Pollack,et al. A computational model of symbiotic composition in evolutionary transitions. , 2003, Bio Systems.

[2] David E. Goldberg,et al. Linkage Identification by Non-monotonicity Detection for Overlapping Functions , 1999, Evolutionary Computation.

[3] D. E. Goldberg,et al. Genetic Algorithms in Search , 1989 .

[4] Masaharu Munetomo,et al. Metropolitan Area Network Design Using GA Based on Hierarchical Linkage Identification , 2003, GECCO.

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

[6] Masaharu Munetomo,et al. Modeling Dependencies of Loci with String Classification According to Fitness Differences , 2004, GECCO.

[7] Masaharu Munetomo,et al. Linkage Identification by Nonlinearity Check for Real-Coded Genetic Algorithms , 2004, GECCO.

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

[9] David E. Goldberg,et al. Learning Linkage , 1996, FOGA.

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

[11] Dirk Thierens,et al. On the complexity of hierarchical problem solving , 2005, GECCO '05.