Use of Genetic Algorithms for Optimal Topology Determination in Back Propagation Neural Networks
A genetic algorithm is applied to evolve neural network topologies suitable for given problem domains. Certain concepts, from the fields of statistics and genetics, are considered with a view to possible future improvements to the genetic algorithm.
KeywordsGenetic Algorithm Root Mean Square Back Propagation Neural Network Evolutionary Stable Strategy Back Propagation Network
Unable to display preview. Download preview PDF.
- 1.Marshall, S. J. and Harrison, R. F., 1991, Optimisation and Training of Feedforward Networks by Genetic Algorithms, 2nd IEE International Conference on Artificial Neural Networks, Bournemouth UK, Nov. 91, p39-43.Google Scholar
- 2.Holland, J. H., 1975, Adaptation in Natural and Artificial Systems, University of Michigan Press.Google Scholar
- 3.Goldberg, D., 1988, Genetic Algorithms for Search, Optimisation and Machine Learning. Addison-Wesley.Google Scholar
- 4.Papadimitrion, C. H. and Steiglitz, K., 1982, Combinatorial Optimisation: Algorithms and Complexity. Prentice-Hall.Google Scholar
- 5.Aarts, E., and Korst, J., 1989, Simulated Annealing and Bolzman Machines (A Stochastic Approach to Combinatorial Optimisation and Neural Computing). John Wiley and Sons.Google Scholar
- 6.Ripley, B. D., Statistical Aspects of Neural Networks, 1993, Proceedings of SemStat, Sandbjerg, Denmark, April 1992. Chapman and Hall.Google Scholar