Theory Re nement with Noisy Data

This paper presents a method for revising an approximate domain theory based on noisy data. The basic idea is to avoid making changes to the theory that account for only a small amount of data. This method is implemented in the EITHER propositional Horn-clause theory revision system. The paper presents empirical results on articially corrupted data to show that this method successfully prevents over-tting. In other words, when the data is noisy, performance on novel test data is considerably better than revising the theory to completely t the data. When the data is not noisy, noise processing causes no signicant degradation in performance. Finally, noise processing increases eciency and decreases the complexity of the resulting theory.