The QBKG System: Generating Explanations From a Non-Discrete Knowledge Representation
暂无分享,去创建一个
The QBKG system produces critical analyses of possible moves for a wide variety of backgammon positions, using a hierarchically structurcd. non-discrete form of knowledge representation. This report compares discrete and continuous representations and reasoning systems, addressing issues of competence, robustness, and explainability. The QBKG system is described and demonstrated.
[1] Terry Winograd,et al. Understanding natural language , 1974 .
[2] Allan Collins,et al. A spreading-activation theory of semantic processing , 1975 .
[3] Edward H. Shortliffe,et al. Production Rules as a Representation for a Knowledge-Based Consultation Program , 1977, Artif. Intell..
[4] Hans J. Berliner,et al. Backgammon Computer Program Beats World Champion , 1980 .
[5] Scott E. Fahlman,et al. NETL: A System for Representing and Using Real-World Knowledge , 1979, CL.