Knowledge acquisition has become a major area of artificial intelligence and cognitive science research. The papers in this book show that the area of knowledge acquisition for knowledge-based systems is still a diverse field in which a large number of research topics are being addressed. However, several main themes run through the papers. First, the issue of integrating knowledge from different sources and tools is a sallent topic in many papers. A second major topic in the papers is that of knowledge modelling. Research in knowledge-based systems emphasizes the use of generic models of reasoning and its underlying knowledge. An important trend in the area of knowledge modelling aims at the formalization of knowledge models. Where the field of knowledge acquisition was without tools and techniques years ago, now there is a rapidly growing body of techniques and tools. Apart from the integrated workbenches already mentioned above, several papers in this book present new tools. Although knowledge acquisition and machine learning have been considered as separate subfields of AI, there is a tendency for the two fields to come together.
This publication combines machine learning techniques with more conventional knowledge elicitation techniques. A framework is presented in which reasoning, problem solving and learning, together form a knowledge intensive system that can acquire knowledge from its own experience.