Title :
Reasoning with unlabeled samples and belief functions
Author :
Vannoorenberghe, Patrick
Author_Institution :
Fac. des Sci., Rouen Univ., Mont Saint Aignan, France
Abstract :
This paper presents a decision rule which allows us to reason with unlabeled samples in the framework of Dempster-Shafer (DS) theory of evidence. Thanks to the power of this theoretical framework to represent different kinds of knowledge (from total ignorance to full knowledge), we propose an extension of a so-called evidential classifier which allows to process learning sets whose labeling has been specified with belief functions. This kind of functions can encode partial knowledge on examples of the learning set. In this context, using unlabeled examples can significantly improve the performance of the classifier. In addition, the proposed methodology constitutes by this way a convergence point between supervised and unsupervised learning.
Keywords :
belief maintenance; cognitive systems; convergence; diagnostic reasoning; knowledge based systems; learning systems; pattern classification; uncertainty handling; unsupervised learning; Dempster-Shafer theory of evidence; belief functions; convergence point; decision rule; encoded partial knowledge; evidential classifier; processed learning sets; reasoning; supervised learning; unlabeled examples; unlabeled samples; unsupervised learning; Convergence; Decision trees; Labeling; Pattern classification; Pattern recognition; Semisupervised learning; Supervised learning; Uncertainty; Unsupervised learning;
Conference_Titel :
Fuzzy Systems, 2003. FUZZ '03. The 12th IEEE International Conference on
Print_ISBN :
0-7803-7810-5
DOI :
10.1109/FUZZ.2003.1206534
