Multiple Knowledge Acquisition Strategies in MOLTKE
Year: 1990
Type: preprint
Abstract: In this paper we will present a design model (in the sense of KADS) for the domain of technical diagnosis. Based on this we will describe the fully implemented expert system shell MOLTKE 3.0, which integrates common knowledge acquisition methods with techniques developed in the fields of Model-Based Diagnosis and Machine Learning, especially Case-Based Reasoning. 1. Introduction When starting a real world expert system project knowledge acquisition is the bottleneck. A main reason for this is the gap between the languages of the domain expert and that used for the implementation by the knowledge engineer. This gap reflects the difference between the cognitive models of the application area the two involved persons have. According to the KADS-group to overcome these shortcomings a conceptual model of the domain has to be developed [1]. Then this conceptual model has to be transfered into a design model. We think that developing a conceptual model has a few drawbacks: . The knowledge of...
DOI: 10.22028/d291-40273
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W180709652
