论文信息 - Rough-sets based learning systems

Rough-sets based learning systems

Let us now make the final conclusions concerning the learning processes in static and expanding systems. In a static system we are able to approximate a new concept and teach the system only that approximation. The relation between the concept and its approximation is stored as a system rule. In an expanding system we can teach the system the exact concept. Concepts learned by the system are used to approximate concepts which have to be learned. In static systems these approximations are replaced by larger approximations by applying system rules. For this reason the number of examples used by the teacher to teach a concept in static systems is greater than the number of examples needed to teach the same concept in expanding systems.

Zbigniew W. Ras | Maria Zemankova

[1] P. Winston. Learning by Augmenting Rules and Accumulating Censors. , 1982 .

[2] Bruce G. Buchanan,et al. Principles of Rule-Based Expert Systems , 1982, Adv. Comput..

[3] Zdzislaw Pawlak,et al. Information systems theoretical foundations , 1981, Inf. Syst..

[4] Ryszard S. Michalski,et al. A Theory and Methodology of Inductive Learning , 1983, Artificial Intelligence.

[5] Patrick Henry Winston,et al. Learning structural descriptions from examples , 1970 .

[6] Janice S. Aikins,et al. Prototypical Knowledge for Expert Systems , 1983, Artif. Intell..

[7] Thomas G. Dietterich,et al. Inductive Learning of Structural Descriptions: Evaluation Criteria and Comparative Review of Selected Methods , 1981, Artif. Intell..