An analytical comparison of some rule-learning programs
Artificial Intelligence
Assessing the artificial intelligence contribution to decision technology
IEEE Transactions on Systems, Man and Cybernetics
Learning Systems: Decision, Simulation, and Control
Learning Systems: Decision, Simulation, and Control
A Mathematical Theory of Communication
A Mathematical Theory of Communication
Elicitation of Knowledge from Multiple Experts Using Network Inference
IEEE Transactions on Knowledge and Data Engineering
Hi-index | 0.00 |
In this paper a paradigm for knowledge acquisition is presented. The paradigm, referred to as Multiexpert Knowledge System (MKS), is based on the philosophy that many decision problems which are candidate expert system applications do not rely on just a single expert for advice but utilize the expertise of many, sometimes conflicting, knowledge sources. Because of the potential for conflict between sources, the contemporary approach to building multiple expert or multiexpert knowledge systems has been to eliminate conflict prior to building the knowledge base. The MKS paradigm accommodates multiple, potentially conflicting experts and uses their expertise in the formulation of new knowledge (rules). These new rules are tested using sequential analysis and organized into a knowledge base by means of an entropy reduction program. Together the MKS paradigm, sequential analysis and entropy reduction are components in the design of an 'interactive' learning expert system which behaves as a 'virtual' expert learning and unlearning new knowledge.