Building expert systems
Rule Based Expert Systems: The Mycin Experiments of the Stanford Heuristic Programming Project (The Addison-Wesley series in artificial intelligence)
Control issues in parallel rule-firing production systems
AAAI'91 Proceedings of the ninth National conference on Artificial intelligence - Volume 1
Matching 100,045 learned rules
AAAI'93 Proceedings of the eleventh national conference on Artificial intelligence
| Hi-index | 0.00 |
Our understanding of how to use large amounts of knowledge to enhance the problem solving capabilities of computer programs is quite limited. Over the past several years a number of knowledge based systems have been developed, and this experience has provided us with a handfull of techniques we can apply in a few domains. What we don't have yet is much of an appreciation of why these techniques work or of the limits of their usefulness In order to take this next step, we need more data. Unfoitunately, the analyses of the expert systems currently being built tend to ignore questions that could provide precisely the data needed. This paper proposes a few questions that it might be worth asking and shows how answers to those questions could begin to give us the understanding we lack.