Title :
A family of cascade NN-like classifiers
Author :
Grabowski, Szymon
Author_Institution :
Comput. Eng. Dept., Tech. Univ. of Lodz, Poland
Abstract :
We propose a family of two-stage classifiers with one common feature: the first stage classifier is an ensemble of classifiers working in parallel and the prediction in this stage is considered confident (and thus final) if and only if all the component classifiers return the same answer. If there is no consensus, the sample is sent to the second stage with a costlier classifier. An attractive accuracy-speed tradeoff of the presented algorithms is experimentally confirmed.
Keywords :
cascade systems; classification; accuracy-speed tradeoff; cascade NN-like classifiers; classifier consensus; classifier prediction confidence level; nearest neighbor; parallel classifier ensemble; surrounding neighborhood; two-stage classifier family; Artificial intelligence; Nearest neighbor searches; Neural networks; Proposals; Testing; Voting;
Conference_Titel :
CAD Systems in Microelectronics, 2003. CADSM 2003. Proceedings of the 7th International Conference. The Experience of Designing and Application of
Print_ISBN :
966-553-278-2
DOI :
10.1109/CADSM.2003.1255134