期刊名称：Lecture Notes in Engineering and Computer Science
印刷版ISSN：2078-0958
电子版ISSN：2078-0966
出版年度：2022
卷号：52
期号：2
语种：English
出版社：Newswood and International Association of Engineers
摘要：Ontology is an effective tool for processing conceptsemantics, and in the ontology learning algorithm, all thesemantic information of each vertex is expressed by a multi?dimensional vector. The essence of ontology learning algorithmis to obtain ontology function in terms of ontology data samples,so as to map each concept in ontology to a real number.Stability is the foundation of the ontology learning algorithmand the guarantee of its generalization ability. This articlerelaxes the original uniformly stable hypothesis and proposesthe concept of locally ontology relaxed stability. And under thesetting of reproducing kernel Hilbert space, the upper bound ofstability is verified. Under the framework of random ontologyalgorithm, the original concept is redefined. The error bounds ingeneral, the reproducing kernel Hilbert space and the stochasticontology learning algorithm frameworks are obtained in termsof their respective stability definitions.
