An architecture for exploring large design spaces
AAAI '98/IAAI '98 Proceedings of the fifteenth national/tenth conference on Artificial intelligence/Innovative applications of artificial intelligence
On the Average Number of Maxima in a Set of Vectors and Applications
Journal of the ACM (JACM)
| Hi-index | 0.00 |
Inference to the best explanation, IBE, (or abduction) requires finding the best explanatory hypothesis, from a set of rival hypotheses, to explain a collection of data. The notion of best, however, is multicriterial and the available rival hypotheses might be variously good according to different criteria. Thus, one can view the abduction problem as that of choosing the best hypothesis from among a set of multicriterially evaluated hypotheses - i.e as a multiple criteria decision making problem. In the absence of a single hypothesis that is the best along all dimensions of goodness, the MCDM problem becomes especially hard. The Seeker-Filter-Viewer architecture provides an effective and natural way to use computer power to assist humans to solve certain classes of MCDM problems. In this paper, we apply an MCDM perspective to the abductive problem of red-cell antibody identification and present the results obtained by using the S-F-V architecture.