Arrow Research search

Author name cluster

Kenneth S. Murray

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

2 papers
1 author row

Possible papers

2

AAAI Conference 1996 Conference Paper

KI: A Tool for Knowledge Integration

  • Kenneth S. Murray

Knowledge integration is the process of incorporating new information into a body of existing knowledge. It involves determining how new and existing knowledge interact and how existing knowledge should be modified to accommodate the new information. KI is a machine learning program that performs knowledge integration. Through actively investigating the interaction of new information with existing knowledge KI is capable of detecting and exploiting a variety of diverse learning opportunities during a single learning episode. Empirical evaluation suggests that KI provides significant assistance to knowledge engineers while integrating new information into a large knowledge base.

IJCAI Conference 1987 Conference Paper

Multiple Convergence: An Approach to Disjunctive Concept Acquisition

  • Kenneth S. Murray

Multiple convergence is proposed as a method for acquiring disjunctive concept descriptions. Disjunctive descriptions are necessary when the concept representation language is insufficiently expressive to satisfy the completeness and consistency requirements of inductive learning with a single conjunction of generalized features. Multiple convergence overcomes this insufficiency by allowing the disjuncts of a complex concept to be acquired independently. By summarizing correlations among features in the training data, disjunctive concepts can provide rich extensions to the representation language which may enhance subsequent learning. This paper presents the benefits of disjunctive concept descriptions and advocates multiple convergence as an approach to their acquisition. Multiple convergence has been implemented in the learning system HYDRA, and a detailed example of its execution is presented.

v2026.09.13