Current page: Information->Indexed and Annotated Bibliography
S. B. Cho and J. H. Kim
ABSTRACT
Recently, in the area of artifificial neural networks, the concept of combining multiple networks has been proposed as a new direction for the development of highl;y reliable neural network systems. In this paper we propose a method fro multinetwork combination based on the fuzzy integral. This technique non-linearly combines objexctive evidence, in the form of a fuzzy membership function, with subjective evaluation of the worth of the individual neural networks with respect to the decision. the experimantal results with the recognition problem of on-line handwriting characters conform the superiority of the presented method to the other voting techniques. 
ECVision indexed and annotated bibliography of cognitive computer vision publications
This bibliography was created by Hilary Buxton and Benoit Gaillard, University of Sussex, as part of ECVision Specific Action 8-1
The complete text version of this BibTeX file is available here: ECVision_bibliography.bib
Combining Multiple Neural Networks by Fuzzy Integral for Robust ClassificationSite generated on Friday, 06 January 2006