摘要
主要研究了本体学习算法在替换一个样本点(RO)情况下的稳定性.定义多个本体学习算法的稳定性相关概念并得到它们之间的相互关系.另外结果还显示RO稳定性是本体学习算法的充分必要条件.
Ontology is a semantic analysis and calculation model,which has been applied to many subjects.The purpose of this paper is to study the RO stability of ontology learning algorithm.Several RO stabilities are defined in ontology learning setting and the relationship among these stabilities are presented.Furthermore,the results manifested reveal that RO stability is a sufficient and necessary condition for ontology learning algorithm.
作者
彭波
高炜
PENG Bo;GAO Wei(School of Information,Yunnan Normal Univcrsity,Kunming 650500,China)
出处
《云南师范大学学报（自然科学版）》
2018年第5期32-38,共7页
Journal of Yunnan Normal University:Natural Sciences Edition
基金
国家自然科学基金资助项目(11761083)
关键词
本体
相似度计算
学习算法
本体亏损函数
稳定性
Ontology
Similarity measure
Learning algorithm
Ontology loss function
Stability
