1986 - Mapping Explanation-Based Generalization onto Soar
نویسندگان
چکیده
Explanation-based generalization (EBG) is a powerful approach to concept formation in which a justifiable concept definition is acquired from a single training example and an underlying theory of how the example is an instance of the concept. Soar is an attempt to build a general cognitive architecture combining general learning, problem solving, and memory capabilities. It includes an independently developed learning mechanism, called chunking, that is similar to but not the same as explanation-based generalization. In this article we clarify the relationship between the explanation-based generalization framework and the Soar/chunking combination by showing how the EBG framework maps onto Soar, how several EBG conceptformation tasks are implemented in Soar, and how the Soar approach suggests answers to some of the outstanding issues in explanation-based generalization.
منابع مشابه
Mapping Explanation-based Learning onto Soar: the Sequel
In past work, chunking in Soar has been analyzed as a variant of explanation-based learning. The components and processes underlying EBL have been mapped to their corresponding components and processes in chunking. The cost and generality of the resulting rules have also been compared. Here we extend that work by analyzing an implementation of EBL within Soar as a sequence of transformations fr...
متن کاملAn Application of Explanation-Based Learning to Discourse Generation and Interpretation
This paper presents a brief description of Explanation-Based Learning (EBL), and argues that it is an approach to machine learning with signi cant potential for use in discourse processing. More speci cally, EBL can be used by systems that model discourse generation as goaldriven behavior, and that model discourse interpretation as recognizing the speaker's discourse goals. As evidence, we desc...
متن کاملLearning by Failing to Explain
Explanation-based Generalization depends on having an explanation on which to base generalization. Thus, a system with an incomplete or intractable explanatory mechanism will not be able to generalize some examples. It is not necessary, in those cases, to give up and resort to purely empirical generalization methods, because the system may already know almost everything it needs to explain the ...
متن کاملA Transformational Analysis of the EBL Utility Problem
Efficiency is a major concern for all problem solving systems. One way of achieving efficiency is the application of learning techniques to speed up problem solving. Accordingly, there has been considerable amount of research on applying explanation-based learning (EBL)(Mitchell, Keller, & Kedar-Cabelli 1986) techniques to problem solving. However, EBL is known to suffer from the utility proble...
متن کاملIntegrated Learning: Controlling Explanation
Similarity-based learning, which invalves largely structural comparisons of instances, and explanation-based learning, a knowledge-intensive method far analyzing instances to build generalized schemata, are two major inductive learning techniques in use in Artificial Intelligence. In this paper, we propose a combination of the two methods-applying explonotion-based techniques during the course ...
متن کامل