核方法驱动的本体函数迭代算法

Kernel Method-driven Ontology Function Iterative Algorithm

机器学习算法在本体中的运用集中在本体最优函数的学习,即通过本体样本点和适当的学习策略得到最优实值函数.核函数由于其在再生性和重构函数上的诸多优点,而被广泛运用于机器学习算法中.在本体函数的优化学习过程,将核方法融入迭代策略中,进而可得到最优的本体函数.实验结果表明,该方法对特定领域本体相似度的计算和本体映射的构建具有较高的准确率.

The application of machine learning algorithms in ontology focuses on the learning of ontology optimal functions,that is,the optimal real-valued functions are obtained through ontology sample points and appropriate learning strategies. Kernel functions are widely used in machine learning algorithms due to their many advantages in regenerative and reconstruction functions. In the optimization learning process of ontology function,the kernel method is integrated into the iterative strategy to obtain the optimal ontology function. The experimental results show that the proposed method has higher accuracy for the calculation of ontology similarity and the construction of ontology mapping in specific domains.