Modular Neuro-Fuzzy Systems Based on Generalized Parametric Triangular Norms
Neuro-fuzzy systems are used for modeling and classification thanks to their advantages such as interpretable knowledge and ability to learn from data. They are similar to neural networks but their design is structured depending on knowledge in the form of fuzzy rules. Final decision is inferred by fuzzy inference using triangular norms. The paper presents modular neuro-fuzzy systems based on parametric classes of generalized conjunction and disjunction operations. The proposed systems are better adjustable to data during learning. Part of this flexibility is achieved by the new operators what do not alter the original knowledge of fuzzy rules. The method described in the paper is tested on several known benchmarks.
Unable to display preview. Download preview PDF.
- 4.Breiman, L.: Bagging predictors. Machine Learning 26(2), 123–140 (1996)Google Scholar
- 5.Jang, R.J.-S., Sun, C.-T., Mizutani, E.: Neuro-Fuzzy and Soft Computing, A Computational Approach to Learning and Machine Intelligence. Prentice Hall, Upper Saddle River (1997)Google Scholar
- 8.Nauck, D., Klawon, F., Kruse, R.: Foundations of Neuro - Fuzzy Systems. John Wiley, Chichester (1997)Google Scholar
- 10.Schapire, R.E.: A brief introduction to boosting. In: Sixteenth International Joint Conference on Artificial Intelligence, pp. 1401–1406 (1999)Google Scholar
- 11.Wang, L.-X.: Adaptive Fuzzy Systems And Control. PTR Prentice Hall, Englewood Cliffs (1994)Google Scholar