Optimization and Interpretation of Rule-Based Classifiers
Machine learning methods are frequently used to create rule-based classifiers. For continuous features linguistic variables used in conditions of the rules are defined by membership functions. These linguistic variables should be optimized at the level of single rules or sets of rules. Assuming the Gaussian uncertainty of input values allows to increase the accuracy of predictions and to estimate probabilities of different classes. Detailed interpretation of relevant rules is possible using (probabilistic) confidence intervals. A real life example of such interpretation is given for personality disorders. The approach to optimization and interpretation described here is applicable to any rule-based system.
KeywordsMembership Function Fuzzy Rule Linguistic Variable Logical Rule Classification Probability
Unable to display preview. Download preview PDF.
- 1.Duch, W., Adamczak, R., Grgbczewski, K. (in print) Methodology of extraction, optimization and application of crisp and fuzzy logical rules. IEEE Transactions on Neural Networks.Google Scholar
- 2.Duch, W., Adamczak, R., Grabczewski, K. (1999) Methodology of extraction, optimization and application of logical rules. Intelligent Information Systems VIII, Ustron, Poland, 14–18. 06. 1999, pp. 22–31Google Scholar
- 4.Duch, W., Adamczak, R., Gr4bczewski, K. (1999) Neural optimization of linguistic variables and membership functions. Int. Conference on Neural Information Processing (ICONIP’99), Perth, Australia, Nov. 1999, Vol. II, pp. 616–621Google Scholar
- 5.Breiman L. (1998) Bias-Variance, regularization, instability and stabilization. In: C. Bishop (ed.) Neural Networks and Machine Learning. Springer VerlagGoogle Scholar
- 6.Duch, W., Jankowski, N. (1999) New neural transfer functions. Neural Computing Surveys 2, 639–658Google Scholar
- 7.Jankowski, N., Kadirkamanathan, V. (1997) Statistical control of RBF-like networks for classification. 7th Int. Conf. on Artificial Neural Networks, Lausanne, Switzerland 1997, pp 385–390, Springer Verlag.Google Scholar
- 8.Jankowski, N., (1999) Ontogenic neural networks and their applications to classification of medical data. PhD thesis (in Polish), Department of Computer Methods, Nicholas Copernicus University, Torun, PolandGoogle Scholar
- 9.Duch W., Adamczak R., Grabczewski K. (1999) Neural methods for analysis of psychometric data. Proc. of Enginnering Applications of Neural Networks (Duch W, ed.), Warsaw, Poland, Sept. 1999, pp. 45–50Google Scholar
- 10.Duch, W., Kucharski, T., Gomula, J., Adamczak, R., (1999) Metody uczenia maszynowego w analizie danych psychometrycznych. Zastosowanie do wielowymiarowego kwestionariusza osobowoki MMPI–WISKAD. Torun, March 1999; 650 pp, ISBN 83–231–0986–9Google Scholar
- 11.Quinlan J.R. (1993) C4. 5: Programs for machine learning. San Mateo, Morgan KaufmanGoogle Scholar
- 13.Duch, W., Adamczak, R., Jankowski, N. (1997) New developments in the Feature Space Mapping model. 3rd Conf. on Neural Networks, Kule, Poland, Oct. 1997, pp. 65–70Google Scholar