Knowledge Acquisition最新文献

This paper presents a general approach to knowledge base refinement which integrates multistrategy learning, active experimentation and guided knowledge elicitation. Three main features characterize this approach. First, knowledge base refinement is based on a multistrategy learning method that dynamically integrates the elementary inferences (such as deduction, analogy, abduction, generalization, specialization, abstraction and concretion) that are employed by the single-strategy learning methods. Second, much of the knowledge needed by the system to refine its knowledge base is generated by the system itself. Therefore, most of the time, the human expert will need only to confirm or reject system-generated hypotheses. Third, the knowledge base refinement process is efficient due to the ability of the multistrategy learner to reuse its reasoning process. The paper illustrates a cooperation between a learning system and a human expert in which the learner performs most of the tasks and the expert helps it in solving the problems that are intrinsically difficult for a learner and relatively easy for an expert.

This paper is concerned with the task of incrementally acquiring and refining the knowledge and algorithms of a knowledge-based system in order to improve its performance over time. In particular, we present the design of DE-KART, a tool whose goal is to provide increasing levels of assistance in acquiring and refining indexing and retrieval knowledge for a knowledge-based retrieval system. DE-KART starts with knowledge that has been entered manually, and increase its level of assistance in acquiring and refining that knowledge, both in terms of the increased level of automation in interacting with users, and in terms of the increased generality of the knowledge. DE-KART is at the intersection of machine learning and knowledge acquisition: it is a first step towards a system which moves along a continuum from interactive knowledge acquisition to increasingly automated machine learning as it acquires more knowledge and experience.

The paper presents an approach to the integration of knowledge acquisition (KA) techniques and explanation-based learning (EBL). Knowledge acquisition techniques are used to delineate a problem class hierarchy for different manufacturing tasks in mechanical engineering. This hierarchy is stepwise formalized into a terminological representation language. The terminological descriptions are then combined with cases of specific manufacturing tasks and their solutions (in the form of production plans). Explanation-based learning is applied to the cases and skeletal plans are automatically constructed for the terminal classes of the problem class hierarchy. Such skeletal plans consist of a dependency structure with a sequence of operators, that can be instantiated to specific plans for all other problems of the class. An evaluation of the proposed KA/EBL integration demonstrates its strengths as well as certain limitations of explanation-based generalization.

We developed a knowledge acquisition system that uses an Explanation-Based Learning domain theory as a knowledge repository from which general knowledge structures can be compiled and then translated by smart translators into the various specialized representations required for the separate expert system modules of a distributed pilot aiding system. We call this two-stage learning-plus-translation process linked learning. This architecture addresses learning for multiple modules with different knowledge representations and performance goals, but which must all perform together in an integrated fashion. It also addresses learning for an intelligent agent which must perform in a real-world, dynamically-changing environment with multiple sources of uncertainty. Finally, it serves as a case study offering insights into the integration of machine learning into the system engineering process for a large knowledge-based system development effort.

Theory revision is the process of making corrections to a flawed or incomplete knowledge base on the basis of examples that expose those problems. The PTR algorithm is a theory revision algorithm that makes use of explicit bias to guide the detection of flawed knowledge base elements. In this paper, we examine the effectiveness of PTR's bias scheme in identifying flawed knowledge base elements, and we propose extensions to the PTR algorithm that support the use of additional bias to guide the process of correcting a flawed element once it has been located.