Committees of Undemocratic Competent Models.

Wlodzislaw Duch,
School of Computer Engineering, Nanyang Technological University, Singapore,
and Department of Informatics, Nicholas Copernicus University,
Grudziadzka 5, 87-100 Torun, Poland.

and Lukasz Itert,
Dept. of Pediatric Informatics, Children's Hospital Research Foundation, Cincinnati, USA, and Department of Informatics, NCU, Torun, Poland.

Final version published in:
Proceedings of the International Conference on Artificial Neural Networks (ICANN) and International Conference on Neural Information Processing (ICONIP), Istanbul, June 2003, pp. 33-36

Committees of classification and approximation models are used to improve accuracy and decrease the variance of individual models. Each model has an equal right to vote (democratic procedure), despite obvious differences in model competence in different regions of the feature space. Adding competence factors to different models before calculation of the committee decision (undemocratic procedure) improves the quality of the committee. A method for creation of a committee of competent models is described and several real-life empirical tests performed. Significant improvement of results is observed.

Paper in PDF, 47 KB,

BACK to the publications of W. Duch.
BACK to the on-line publications of the Department of Informatics, NCU.