COMBINING ROUGH SETS LEARNING-METHOD AND NEURAL LEARNING-METHOD TO DEAL WITH UNCERTAIN AND IMPRECISE INFORMATION

Any system designed to reason about the real world must be capable of dealing with uncertainty. The complexity of the real world and the finite size of most knowledge bases pose significant difficulties for the traditional concept of the learning system. Experience has shown that many learning paradigms fail to scale up to those problems. One response to these failures has been to construct systems which use multiple learning paradigms. Thus the strengths of one paradigm counterbalance some of the weaknesses of the others. As a result the effectiveness of the overall system will be enhanced. Consequently, integrated techniques have been widespread over the last years. A multistrategy which addresses those issues is presented. This approach joins two forms of learning, the technique of neural networks and rough sets. These seem at first quite different but they share the common ability to work well in a natural environment. In a closed loop fashion we will achieve more robust concept learning capabilities for a variety of difficult classification tasks. The objective of integration is twofold: (i) to improve the overall classification effectiveness of learned objects' description, (ii) to refine the dependency factors of the rules.