Theory Revision via Prior Operationalization
نویسنده
چکیده
Research in machine learning often focuses either on inductive learning learning from experience with minimal reliance on prior theory or, more recently, on explanation-based learning deducing general descriptions from theories with minimal reliance on experience. Theory revision unites these two concerns: one must revise one’s theory in the light of experience, but one must simultaneously use information implicit in the theory in order to guide the revision process. This paper focuses on the second step of a unified three-step method for solving theory revision problems for certain classes of empirical theories. Test results for the first two phases of this approach are reported.
منابع مشابه
Reasoning about Locations in Theory and Practice
Locational reasoning plays an important role in many applications of AI problem-solving systems, yet has remained a relatively unexplored area of research. This paper addresses both theoretical and practical issues relevant to reasoning about locations. We de ne several theories of location designed for use in various settings, along with a sound and complete belief revision calculus for each t...
متن کاملPazzani and C. Brunk. Detecting and Correcting Errors in Rule-based Expert Systems: an Integration of Empirical and Explanation-based Learning. in Proceedings of the 5th Knowledge Acquisition for Knowledge-based Systems Workshop
program plan [ Johnson, 1986 ] , or existing correct program [ Murray, 1988 ] . By comparison, PDS6 and Forte are dynamic. They run a program on speci c examples, detect errors, and use them to revise the program. 2 Consequently, dynamic methods require only partial, extensional de nitions of programs. This is an important advantage since formal speci cations are frequently unavailable. Systems...
متن کاملTheory Reduction, eory
This paper presents an approach to retranslation, the third and final step of the theory reduction approach to solving theory revision problems [3,4]. Retranslation involves putting a modified “operationalized,” or “reduced,” version of the desired revised theory back into the entire language of the original theory. This step is desirable for a number of reasons, not least of which is the need ...
متن کاملFuzzy Set Theory and Concepts: A Proposal for Concept Formation and Operationalization
The quantity-quality debate in social sciences also concerns concept formation and operationalization. The first approach has strong naturalist assumptions, while the second one focuses on the historical specificity of concepts. The solution to overcome this divide would be finding a path which balances the two perspectives. In this article we argue that fuzzy set theory can be a helpful tool f...
متن کاملBridging Jeffrey's Rule, AGM Revision and Dempster Conditioning in the Theory of Evidence
Belief revision characterizes the process of revising an agent’s beliefs when receiving new evidence. In the field of artificial intelligence, revision strategies have been extensively studied in the context of logic-based formalisms and probability kinematics. However, so far there is not much literature on this topic in evidence theory. In contrast, combination rules proposed so far in the th...
متن کامل