| A GENERAL CRITERION FOR MEASURING (2007) | |||||||||||||||
Abstract | |||||||||||||||
| An important aspect of any learning method is an evaluation of the learned knowledge, in particular, an evaluation of the plausibility and usefulness of concept descriptions that are being created. This paper presents a new, general method for evaluating concept descriptions. The method applies not only to the conventional logic-style concept descriptions, but also to two-tiered descriptions that characterize imprecise and/or context-dependent concepts, such concepts are called as flexible. In such descriptions, the fu:st tier specifies typical and idealized concept properties, and the second tier describes the variability and allowed modifications of these properties in different contexts, and exceptional cases. Another novel feature of the measure is that it takes into consideration the typicality of cases covered by the description. In the proposed measure, the quality of a concept description depends on three major criteria: the accuracy, the comprehensibility and the cost. To illustrate the measure, two alternative descriptions of the concept "chair " are evaluated. This work was done in the context of | |||||||||||||||
Publication details | |||||||||||||||
| |||||||||||||||