An Hybrid System for Continuous Learning
We propose a Multiple Neural Networks system for dynamic environments, where one or more neural nets could no longer be able to properly operate, due to partial changes in some of the characteristics of the individuals. We assume that each expert network has a reliability factor that can be dynamically re-evaluated on the ground of the global recognition operated by the overall group. Since the net’s degree of reliability is defined as the probability that the net is giving the desired output, in case of conflicts between the outputs of the various nets the re-evaluation of their degrees of reliability can be simply performed on the basis of the Bayes Rule. The new vector of reliability will be used for making the final choice, by applying two algorithms, the Inclusion based and the Weighted one over all the maximally consistent subsets of the global outcome.
KeywordsMultiple Neural Networks Hybrid System Bayesian Conditioning
Unable to display preview. Download preview PDF.
- 3.Benferhat, S., Cayrol, C., Dubois, D., Lang, J., Prade, H.: Inconsistency management and prioritized syntax-based entailment. In: Proceedings of the 13th International Joint Conference on Artificial Intelligence (IJCAI 1993), pp. 640–645 (1993)Google Scholar
- 4.Gärdenfors, P.: Belief Revision. Cambridge Tracts in Theoretical Computer Science, vol. 29 (December 2003)Google Scholar
- 5.Tolba, A.S., El-Baz, A.H., El-Harby, A.A.: Face recognition a literature review. International Journal of Signal Processing 2, 88–103 (2006)Google Scholar
- 9.Kohonen, T., Hynninen, J., Kangas, J., Laaksonen, J., Torkkola, K.: Lvq Pak: The Learning Vector Quantization Program Package (1995)Google Scholar
- 10.Kohonen, T.: Learning vector quantization. In: Self-Organising Maps, 3rd edn. Springer Series in Information Sciences. Springer, Heidelberg (1995)Google Scholar
- 12.Dragoni, A.F.: Belief revision: from theory to practice. The Knowledge Engineering Review, 147–179 (2001)Google Scholar