M. L. P. Optimal Topology via Genetic Algorithms
In the paper a Genetic Algorithm in order to select the optimal topology of a Multi Layer Perceptron is adopted. Two different problems are considered. The first one is to select the optimal number of neurons in a structure with one hidden layer. The second one is the choice of the number of layers into which a fixed number of neurons has to be arranged, to solve a given problem. To this aim, a suitable set of genetic operators has been introduced.
KeywordsGenetic Algorithm Hide Layer Optimal Topology Testing Phase Genetic Operator
Unable to display preview. Download preview PDF.
- P. Arena, L. Fortuna, S. Graziani, G. Nunnari, “A monitoring approach for the design of a multi-layer neural network”, COMADEM’ 91, Southampton, U:KGoogle Scholar
- J. D. Schaffer, R. Caruana, L. Eshelman, “Using genetic search to exploit the emergent behavior of neural network”, Phillips Laboratories 1989Google Scholar
- S. A. Harp, T. Samad “Genetic Synthesis of neural network architecture”, Handbook of genetic algorithms, L. Davis, Van Nostrand Reinhold, 1991Google Scholar
- P. Arena, L. Fortuna, S. Graziani, G. Muscato, “A real-time implementation of a multi-layer perceptron with automatic tuning of learning parameters” Algorithms and architecture for real-time control, IFAC Workshop Series, N. 4, 1992Google Scholar
- P. Arena, R. Caponetto, L. Fortuna, M.G. Xibilia, “Genetic algorithm to select optimal neural network topology” 35-th Midwest Conference on Circuits and Systems, Washington, U.S.A., August 1992Google Scholar
- D. E. Goldberg, “Genetic algorithms in search, optimization & machine learning”, Addison-Wesley, 1984Google Scholar
- D. E. Rumelhart, G. E. Hinton and R.J. Williams, “Learning internal represntation by error propagation”, Parallel Distributed Processing: Exploration in the microstructure of cognition, D. E. Rumelhart and J. E. McLelland, Cambridge, Mass: MIT Press, 1986, pp. 303–314Google Scholar
- K. S. Narendra, “Identification and control of dynamical systems using neural network”, IEEE Trans. on Neural Network, No. 1, March 1990Google Scholar