随机梯度下降多重分割本体算法的工程应用  

Engineering application for the stochastic gradient descent multi-dividing ontology algorithm

作　　者：彭波[1] 高炜[1] 

机构地区：[1]云南师范大学信息学院,云南昆明650500

出　　处：《苏州科技学院学报（自然科学版）》2015年第1期49-53,共5页Journal of Suzhou University of Science and Technology （Natural Science Edition）

基　　金：国家自然科学基金资助项目(60903131);教育部科学技术研究重点项目(210210)

摘　　要：随机梯度下降多重分割本体算法是通过对步长和步长序列进行控制,迭代优化正则经验误差模型而实现的。该算法已从理论的角度得到了有关学习率的证明。从具体本体应用的角度出发,描述算法如何与实际工程相结合。同时,将算法作用于基因本体和计算机软件本体中,说明算法对这些工程应用领域都具有较高的效率。The stochastic gradient descent multi-dividing algorithm was obtained in terms of the step and step sequences control and the iterative optimization of the regularization experience error model. The result on learn-ing rate for this algorithm was proved from the theoretical point of view. In this paper,from the perspective of specific application,we described the technology on combining the algorithm with real engineering. Furthermore,the algorithm was applied to areas of the gene ontology and computer software ontology to present its high effi-ciency for these engineering applications.

关 键 词：本体 相似度 本体映射 步长序列 梯度下降 

分 类 号：TP393.092[自动化与计算机技术—计算机应用技术]