Fragment as a Small Evidence of the Building Blocks Existence

Building Blocks (BBs) can be considered as a plausible explanation for the success of Genetic Algorithms. The schema theorem can be interpreted as a support for Building Block Hypothesis. However, due to the nature of BBs that are dependent on the problems and the encoding of the chromosome, their behaviors are difficult to analyze. The aim of this work is to show the behavior of BBs processing. Toward this goal, a simplified definition of BBs, called Fragments is proposed. Fragments are similar contiguous bits found in highly fit chromosomes. Using this concept, genetic operations are designed to avoid disruption of BBs. Two operators are proposed, Fragment identification and Fragment composition. Experiments are designed to illustrate two aspects. One is the behavior of BBs processing and the other is the performance of the proposed GA incorporating these operators. The results of the experiments give a clear view of BBs processing. The performance of the proposed algorithm is shown to be superior to the competing algorithms for the Additively Decomposable Functions.

[1]  X. Yao,et al.  Analysing crossover operators by search step size , 1997, Proceedings of 1997 IEEE International Conference on Evolutionary Computation (ICEC '97).

[2]  Kenneth A. De Jong,et al.  A formal analysis of the role of multi-point crossover in genetic algorithms , 1992, Annals of Mathematics and Artificial Intelligence.

[3]  Hillol Kargupta,et al.  The Gene Expression Messy Genetic Algorithm , 1996, Proceedings of IEEE International Conference on Evolutionary Computation.

[4]  John J. Grefenstette,et al.  Deception Considered Harmful , 1992, FOGA.

[5]  Dirk Thierens,et al.  Toward a Better Understanding of Mixing in Genetic Algorithms , 1993 .

[6]  Jordan B. Pollack,et al.  Modeling Building-Block Interdependency , 1998, PPSN.

[7]  Patricia J. Riddle,et al.  Expected Rates of Building Block Discovery, Retention and Combination Under 1-Point and Uniform Crossover , 2004, PPSN.

[8]  Kenneth A. De Jong,et al.  An Analysis of the Interacting Roles of Population Size and Crossover in Genetic Algorithms , 1990, PPSN.

[9]  Christopher R. Stephens,et al.  Schemata Evolution and Building Blocks , 1999, Evolutionary Computation.

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

[11]  David E. Goldberg,et al.  Bayesian Optimization Algorithm: From Single Level to Hierarchy , 2002 .

[12]  Kalyanmoy Deb,et al.  RapidAccurate Optimization of Difficult Problems Using Fast Messy Genetic Algorithms , 1993, ICGA.

[13]  J. A. Lozano,et al.  Towards a New Evolutionary Computation: Advances on Estimation of Distribution Algorithms (Studies in Fuzziness and Soft Computing) , 2006 .

[14]  G. Harik.  Learning gene linkage to efficiently solve problems of bounded difficulty using genetic algorithms , 1997 .

[15]  J. Pollack,et al.  Hierarchically consistent test problems for genetic algorithms , 1999, Proceedings of the 1999 Congress on Evolutionary Computation-CEC99 (Cat. No. 99TH8406).

[16]  David E. Goldberg,et al.  The Design of Innovation: Lessons from and for Competent Genetic Algorithms , 2002 .

[17]  Melanie Mitchell,et al.  What makes a problem hard for a genetic algorithm? Some anomalous results and their explanation , 1993, Machine Learning.

[18]  Emanuel Falkenauer,et al.  The worth of the uniform [uniform crossover] , 1999, Proceedings of the 1999 Congress on Evolutionary Computation-CEC99 (Cat. No. 99TH8406).

[19]  D. Goldberg,et al.  BOA: the Bayesian optimization algorithm , 1999 .

[20]  W. Rudnick.  Genetic algorithms and fitness variance with an application to the automated design of artificial neural networks , 1992 .

[21]  Martin Pelikan,et al.  Scalable Optimization via Probabilistic Modeling , 2006, Studies in Computational Intelligence.

[22]  Thomas Jansen,et al.  A building-block royal road where crossover is provably essential , 2007, GECCO '07.

[23]  Melanie Mitchell,et al.  The royal road for genetic algorithms: Fitness landscapes and GA performance , 1991 .

[24]  J. A. Lozano,et al.  Estimation of Distribution Algorithms: A New Tool for Evolutionary Computation , 2001 .

[25]  Prabhas Chongstitvatana,et al.  Chi-Square Matrix: An Approach for Building-Block Identification , 2004, ASIAN.

[26]  Prabhas Chongstitvatana,et al.  A quantitative approach for validating the building-block hypothesis , 2005, 2005 IEEE Congress on Evolutionary Computation.

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

[28]  D. Goldberg,et al.  Linkage learning through probabilistic expression , 2000 .

[29]  Kalyanmoy Deb,et al.  Genetic Algorithms, Noise, and the Sizing of Populations , 1992, Complex Syst..

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

[31]  Christopher R. Stephens,et al.  Schemata as Building Blocks: Does Size Matter? , 2000, FOGA.