Meta-Typicalness Approach to Reliable Classification

We propose a meta-typicalness approach to apply the typicalness framework for any type of classifiers. The approach can be used to construct classifiers with specified classification performance. Experiments show that the approach results in classifiers that can outperform an existing typicalness-based classifier.

• Type: Conference
• Year: 2006
• Where: ECAI
• Authors: Evgueni N. Smirnov, Stijn Vanderlooy, Ida G. Sprinkhuizen-Kuyper
• Keywords: Artificial Intelligence, Classification Performance, ECAI 2006, Meta-typicalness Approach, Typicalness Framework