http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Cas, Caro Lu 대한전자공학회 1992 HICEC:Harbin International Conference on Electroni Vol.1 No.1
In this paper, an ART2 type architecture is proposed for approximate inference from a set of production rules and an observed premise. The antecedents and consequents of the rules and the observation can be fuzzy, and the rule set may be incomplete. The reasoning method is based on a recently proposed approximate analogical reasoning meta-algorithm as well as some proposed modifications that make it more deductive. It is possible to devise a training algorithm so that the proposed neural network can be used as a reprogrammable inference engine.