基于区间值模糊集的学习空间描述及其模糊归纳学习算法研究

Investigation on Description of Learning Space Based-on Interval Fuzzy Sets and Fuzzy Inductive Learning Algorithm

本文基于区间值模糊集理论，将归纳学习空间予以模糊化，使其更具有普遍性。为了度量概念的可学习性能，新定义了区分区间概念。运用对基本事件空间划分的加细操作，来改进要学习的概念之区分区间值，并进而改进其归纳学习效果。据此，本文提出了模糊归纳学习问题的模糊学习算法ＩＬＡ。算法ＩＬＡ能根据专家提供的有关概念实例集，学习出关于概念的模糊推理规则。文中最后还对ＩＬＡ的算法复杂度进行了分析。

Based on interval fuzzy sets,the inductive learning space is fuzzified,the distinction interval is newly defined to measure the learnable performance of concepts to be learned. By applying the operator of partition for basic event space,the value of distinction interval and the effieiency of inductive learning for concepts to be learned are improved.Fuzzy inductive learning Algorithm (ILA) is presented for fuzzy inductive Learning problems. In terms of the example sets of concepts offered by experts,algorithm ILA can learn fuzzy inference rules about concepts to be learned. Finally,the complexity of algorithm ILA is also discussed.