The synthesis of the ranked neural networks applying genetic algorithm with the dynamic probability of mutation
The real problem connected with the construction of neural networks is to appoint the number of elements (neurons) and the connection structure. The algorithms, which construct the classification networks using ranked layers allow to establish the number of neurons and weights of their connections on the basis of training data set. In this paper, the method of ranked layer construction, using genetic algorithm has been presented. The applying the genetic algorithm leads to obtaining the network with less number of elements, hence the investigated network is of more ability to generalize information. Such a smaller network preserves its given classification property referring to the data of training set. In addition, applying of the genetic algorithm allows to use in the construction process any neuron activation function, e. g. rectangular activation function. This feature results in considerable reduction of the network size.
Unable to display preview. Download preview PDF.
- [Bobr92]Bobrowski L.,“The ranked networks of formal neurons”, Biocybernetics and Biomedical Engineering, vol.12, no.1–4, 1992.Google Scholar
- [Bobr94]Bobrowski L., “Ranked layer of formal neurons and their applications in features extraction” (in polish), Proc. First National Conference on Neural Networks, Czcestochowa, 1994.Google Scholar
- [DeJo75]De Jong K. A.,“An analysis of the behavior of a class of genetic adaptive systems”, Ph.D. dissertation, Univ. Michigan, 1975.Google Scholar
- [Gold89]Goldberg D. E., “Genetic Algorithms in Search, Optimization and Machine Learning”, Reading, MA: Addison-Wesley, 1989.Google Scholar
- [Holl75]Holland J. H. “Adaptation in Natural and Artificial Systems”, Ann Arbor, MI: University of Michigan Press, 1975.Google Scholar
- [Lis94]Lis J., “The Algorithms of neural networks for Clssification Purposes”, Ph.D. dissertation, Institute of Biocybernetics and Biomedical Engineering of Polish Academy of Sciences, Warsaw, 1994.Google Scholar
- [March90]Marchand M., Golea M., Rujan P., “A convergence theorem for sequential learning in two-layer Perceptrons”, Europhysics Latters, vol.11, no.6, 1990.Google Scholar
- [Mich92]Michalewicz Z., “Genetic Algorithms+Data Structures=Evolution Programs”. Springer-Verlag. 1992.Google Scholar