Journal of Intelligence and Information Systems (지능정보연구)

Korea Intelligent Information System Society (한국지능정보시스템학회)
권호 표지

A Meta-learning Approach that Learns the Bias of a Classifier

  • 김영준 (상명대학교 전자계산학과) ;
  • 홍철의 (상명대학교 정보과학과) ;
  • 김윤호 (상명대학교 소프트웨어학과)
  • Published : 1997.12.01
Download PDF
⟨ Previous Next ⟩

Abstract

DELVAUX is an inductive learning environment that learns Bayesian classification rules from a set o examples. In DELVAUX, a genetic a, pp.oach is employed to learn the best rule-set, in which a population consists of rule-sets and rule-sets generate offspring by exchanging some of their rules. We have explored a meta-learning a, pp.oach in the DELVAUX learning environment to improve the classification performance of the DELVAUX system. The meta-learning a, pp.oach learns the bias of a classifier so that it can evaluate the prediction made by the classifier for a given example and thereby improve the overall performance of a classifier system. The paper discusses the meta-learning a, pp.oach in details and presents some empirical results that show the improvement we can achieve with the meta-learning a, pp.oach.

Keywords

References

  1. Proceedings of the Second International Working Notes on Multistrategy Learning Experiments on multistrategy learning by meta-learning Chan, P.;S. Stolfo
  2. in Proc. National Computer Conference Subjective Bayesian methods for rule-based inference systems Duda, R.;P. Hart;J. Nilsson
  3. IEEE Trans. Syst., Man, Cybern v.SMC-34 Decision making involving imperfect knowledge Eick, C. F.;N. Metha
  4. in Int. Conf. on Tools with Artificial Intelligence Enhancing diversity for a genetic algorithm learning environment for classification tasks Eick, C. F.;Y-J. Kim;N. Secomandi
  5. in The Third World Congress on Expert Systems DELVAUX-An Environment that Learns Bayesian Rule-sets with Genetic Algorithms Eick, C. F.;Y-J. Kim;N. Secomandi;E. Toto
  6. Machine Learning v.13 A knowledge-intensive genetic algorithm for supervised learning Janikow, C.
  7. in The 4th Annual Conference on Evolutionary Programming Multi-rule-set dicision-making schemes for classification tasks Kim, Y-J.;C. F. Eick
  8. in Third IEEE International Conference of Fuzzy Systems Design of sophisticated fuzzy logic controllers using genetic algorithms Kim, C.;Y. Li
  9. in Third IEEE International Conference on Fuzzy System Genetic design of fuzzy controller: The cart and jointed pole problem Mark, G. Cooper;Jacques Vidal
  10. in Proc. 3rd Int. Conf. Genetic Algorithms A critical review of classifier systems Wilson, S.;D. Goldberg
  11. Journal of Molecular Biology v.225 A hybird systems for protein secondary structure prediction Zhang, X.;J. Mesirov;D. Waltz