Incremental Case-Based Learning Through Introspective Reasoning About Knowledge Goals

通过关于知识目标的内省推理进行增量基于案例的学习

• 批准号: 9009710
• 负责人: Ashwin Ram
• 金额: $ 6.7万
• 依托单位: Georgia Tech Research Corporation
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 1990
• 资助国家: 美国
• 起止时间: 1990-09-01 至 1993-02-28
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=9009710&HistoricalAwards=false
• 关键词: Incremental; Case; Based; Learning; Through

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.

本研究将探讨推理机如何提高其 理解一个不完全理解的领域， 将已知知识应用于新问题， 域 最近的人工智能工作涉及使用过去的问题。 推理者的记忆中储存的理解小说的经验 计划新的目标，或解决新的问题。 然而，这个过程假设过去的经验是好的， 理解并提供良好的“教训”，用于未来 situations. 这种假设通常是错误的，当一个人 了解一个新的领域，因为遇到的情况 以前在这个领域可能不被理解 彻底 这项研究将开发出一种技术， 推理机可以（a）使用可能不完全 （B）保持明确的 （c）通过填补知识库中的“空白”来学习 在获得所需信息时填补这些空白， 因此（d）逐步加深对该领域的了解。 这项研究之所以重要，有几个原因。 上 理论方面，它将有助于我们理解 学习、解释和基于经验的推理。 上 从实用的角度来看，它将为技术提供基础， 这将使我们能够设计出实用的共振系统， 通过经验学习和提高自己的表现。