Comparison and Analysis of Mutation-based Evolutionary Algorithms for ANN Parameters Optimization

distribution is considered. The proposed approach consists of two components; the first component describes the ANN " internal " architecture and depends on a total number of hidden layers and an average number of neurons on hidden layers. This relationship is determined by the Fermi-Dirac-like function. The second component changes its value depending on the fitness of a chromosome, exposed to mutation. Including phenotype and genotype information about the problem the proposed strategy adjusts the mutation strength to a given ANN architecture and a mutated chromosome simultaneously.

[1]  Wolfram-Manfred Lippe.  Soft-Computing: mit Neuronalen Netzen, Fuzzy-Logic und Evolutionären Algorithmen (eXamen.press) , 2007 .

[2]  Xin Yao,et al.  Evolutionary programming made faster , 1999, IEEE Trans. Evol. Comput..

[3]  R. Hinterding,et al.  Gaussian mutation and self-adaption for numeric genetic algorithms , 1995, Proceedings of 1995 IEEE International Conference on Evolutionary Computation.

[4]  G. B. Fogel,et al.  Evolved neural networks for quantitative structure-activity relationships of anti-HIV compounds , 2002, Proceedings of the 2002 Congress on Evolutionary Computation. CEC'02 (Cat. No.02TH8600).

[5]  X. Yao.  Evolving Artificial Neural Networks , 1999 .

[6]  Christophe Giraud-Carrier,et al.  Evolutionary Programming of Near-Optimal Neural Networks , 1999, ICANNGA.

[7]  David B. Fogel,et al.  Case studies in applying fitness distributions in evolutionary algorithms: I. Simple neural networks and Gaussion mutation , 2000, SPIE Defense + Commercial Sensing.

[8]  David B. Fogel,et al.  Revisiting evolutionary programming , 1998, Defense, Security, and Sensing.

[9]  Juan Julián Merelo Guervós,et al.  Evolving Multilayer Perceptrons , 2000, Neural Processing Letters.

[10]  Xin Yao,et al.  Fast Evolutionary Programming , 1996, Evolutionary Programming.

[11]  C. J. Adkins.  Thermodynamics and statistical mechanics , 1972, Nature.

[12]  J. Urgen Branke.  Evolutionary Approaches to Dynamic Optimization Problems -a Survey , 1999 .

[13]  Zbigniew Michalewicz,et al.  Parameter Control in Evolutionary Algorithms , 2007, Parameter Setting in Evolutionary Algorithms.

[14]  Xin Yao,et al.  Fast Evolution Strategies , 1997, Evolutionary Programming.

[15]  David B. Fogel,et al.  A Comparison of Evolutionary Programming and Genetic Algorithms on Selected Constrained Optimization Problems , 1995, Simul..

[16]  David B. Fogel,et al.  Evolving Neural Networks: Selected Medical Applications and the Effects of Variation Operators , 2003 .

[17]  Hussein A. Abbass,et al.  Simultaneous Evolution of Architectures and Connection Weights in ANNs , 2001 .