A Genetic Algorithm with Modified Tournament Selection and Efficient Deterministic Mutation for Evolving Neural Network
In this paper, we present a genetic algorithm (GA) based on tournament selection (TS) and deterministic mutation (DM) to evolve neural network systems. We use population diversity to determine the mutation probability for sustaining the convergence capacity and preventing local optimum problem of GA. In addition, we consider population that have a worst fitness and best fitness value for tournament selection to fast convergence. Experimental results with mathematical problems and pattern recognition problem show that the proposed method enhance the convergence capacity about 34.5% and reduce computation power about 40% compared with the conventional method.
KeywordsGenetic Algorithm Mutation Probability Tournament Selection Gray Code Neural Network System
Unable to display preview. Download preview PDF.
- 1.Hicklin, J., Demuth, H.: Modeling Neural Networks on the MPP. In: Proceeding of 2nd Symposium on the Frontiers of Massively Parallel Computation, pp. 39–42 (1988)Google Scholar
- 2.Ho, C.W., Lee, K.H., Leung, K.S.: A Genetic Algorithm Based on Mutation and Crossover with Adaptive Probabilities. In: Proceeding of the 1999 Congress on Evolutionary Computation, pp. 768–775 (1999)Google Scholar
- 4.Kim, J.J., Choi, Y.H., Lee, C.H., Chung, D.J.: Implementation of a High-Performance Genetic Algorithm Processor for Hardware Optimization. IEICE Trans. Electron (1), 195–203 (2002)Google Scholar
- 5.Hesser, M.R.: Towords an Optimal Mutation Probability for Genetic Algorithms. In: Proceedings of the first Conference on Parallel Problem Solving from Nature, pp. 23–32 (1990)Google Scholar
- 6.Gong, D., Pan, F., Sun, X.: Research on a Novel Adaptive Genetic Algorithm. In: Proceeding of the 2002 IEEE International Symposium on Industrial Electronics, pp. 357–359 (2002)Google Scholar