Evolutionary Search with Erosion of Quality Peaks
The aim of this note is to find effective evolutionary algorithm specialized in landscape saddle crossing. Emphasis is put on the modification of the Evolutionary Search with Soft Selection algorithm which is enriched by a mechanism called the Deterioration of the Objective Function. Formal analysis is used in order to find the best approximation of the local peak which has to be eroded by the trapped population. Simulation results confirm the assumed effectiveness of the method.
KeywordsGlobal Optimization Evolutionary Search Efficient Global Optimization Intelligent Information System Local Optimization Algorithm
Unable to display preview. Download preview PDF.
- 1.Fogel L.G., Owens A.J. and Walsh M.J. (1996) Artificial intelligence through simulated evolution. Wiley, New YorkGoogle Scholar
- 3.Galar R. (1990) Soft selection in random global adaptation in R n. A biocybernetic model of development. Technical University Press, Wroclaw (in Polish)Google Scholar
- 4.Holland J.H. (1975) Adaptation in natural and artificial systems. The University of Michigan Press, Ann Arbor, MIGoogle Scholar
- 5.Karcz-Dulgba I. (1992) Simulation of evolutionary processes as a tool of global optimization in W1. Ph.D. Thesis, Technical University of Wroclaw, Wroclaw (in Polish)Google Scholar
- 6.Karcz-Dulgba I. (1997) Some convergence aspects of evolutionary search with soft selection method. In: Evolutionary Algorithms and Global Optimization, 2nd Conference at Rytro, Poland, September 15–19, 1997, Warsaw University of Technology Press, Warsaw, 113–120Google Scholar
- 7.Obuchowicz A. (1997) The evolutionary search with soft selection and deterioration of the objective fuction. In: Klopotek M., Michalewicz M. (Eds.) Intelligent Information Systems IIS’97, 6th International Symposium at Zakopane, Poland, June 9–15, 1997, Polish Academy of Sciences Press, Warsaw, 288–295Google Scholar
- 8.Obuchowicz A. and Korbicz J. (1998) Evolutionary search with soft selection and forced direction of mutation.In: Klopotek M., Michalewicz M. (Eds.) Intelligent Information Systems IIS’97, 6th International Symposium at Malbork, Poland,June 15–19, 1998, Polish Academy of Sciences Press, Warsaw, 300–309Google Scholar
- 9.Obuchowicz A. and Korbicz J. (1999) Evolutionary search with soft selection algorithms in parameter optimization. In: Wyrzykowski R., Mochnacki B., Piech H., Szopa J. (Eds.) Parallel Processing and Applied Mathematics PPAM’99, 3rd International Conference at Kazimierz Dolny, Poland, September 14–19, 1999, Technical University of Czestochowa Press, Czestochowa, 578–586Google Scholar
- 10.Obuchowicz A. and Patan K. (1997) About some Modification of Evolutionary Search with Soft Selection Algorithm. In: Evolutionary Algorithms and Global Optimization, 2nd Conference at Rytro, Poland, September 15–19, 1997, Warsaw University of Technology Press, Warsaw, 193–200Google Scholar
- 11.Rechenberg I. (1965) Cybernetic solution path of an experimental problem. Roy. Aircr. Establ., libr. Transl. 1122, Farnborough, Hants., UKGoogle Scholar