Abstract
Humans do not always learn using the same knowledge representation. They use concrete knowledge representation at first, but they gradually come to use abstract one as they learn more. We have studied a system that switches knowledge representation, reconstructs knowledge set and switches reasoning method. The system reasons with one knowledge set from all stored data set using a knowledge generation method in a knowledge representation. For complex problems, however, human combines several knowledge sets in one knowledge representation. In this paper, we propose a framework that a new knowledge set generated from the stored data after the generation of the previous knowledge set is added to the knowledge representation. Then it is necessary for the system to use a knowledge set combining results from several knowledge sets. This knowledge set is tuned using the generalized delta rule. We compare this method to the previous method. The system reasons with one knowledge set from all stored data set using a kenowledge generation method in a knowledge representation. For complex problems, however, human combines several knowledge sets in one knowledge representation. In this paper, we propose a framework that a new knowledge set generated from the stored data after the generation of the previous knowledge set is added to the knowledge representation. The system combine results obtained from several knowledge sets. Then the system reconstructs knowledge set for combining results obtained from several knowledge sets. The extended system uses several knowledge sets from several stored data sets divided by the criteria of oldness. And we compare this method to the previous one.
