高斯核支持向量机分类和模型参数选择研究

Support Vector Machine with Gauss Kernel Classified Method and Model Selection

支持向量机(SupportVectorMachine,SVM)是近几年发展起来的机器学习新方法,以高斯核为核函数的支持向量机在实际应用中表现出良好的学习性能,被广泛应用于模式分类中。论文研究了高斯核支持向量机分类在IRIS分类问题上的应用,并结合结构风险最小化原则分析了误差惩罚参数C和高斯核宽度σ对SVM性能的影响,最后通过数值实验进一步分析了这种影响。

Support Vector Machine（SVM） is a novel machine learning method.Gauss kernel function is widely used in support vector machine because of its good properities.In this paper,the classification algorithm of support vector with Gaussian kernel and its application in IRIS are discussed.Based on structural risk minimization principal,the influences of the error penalty parameter C and the kernel parameter σ on support vector machine＇s generalization ability are studied.Finally experimental results further analyze the influences.