Incremental Case-Based Learning Through Introspective Reasoning About Knowledge Goals

点击翻译按钮获取中文摘要

This research will investigate how a reasoner can improve its understanding of an incompletely understood domain through the application of what it already knows to novel problms in that domain. Recent work in AI has dealt with the issue of using past experience stored in the reasoner's memory to understand novel situations, plan for novel goals, or solve novel problems. However, this process assumes that past experiences are well understood and provide good "lessons" to be used for future situations. This assumption is usually false when one is learning about a novel domain, since situations encountered previously in this domain might not have been understood completely. The research will develop techniques by which a reasoner can (a) use domain knowledge that may not be completely understood to solve novel problems, (b) maintain an explicit model of the "gaps" in its knowledge base, (c) learn by filling in these gaps when the information it needs become available, and hence (d) gradually evolve a better understanding of the domain. This research is important for several reasons. On the theoretical side, it will contribute to our understanding of learning, explanation, and experience-based reasoning. On the practical side, it will provide the foundations for technology that will allow us to design practical resoning systems that can learn and improve their own performance through experience.