基于混沌优化算法的支持向量机参数选取方法

Selection of SVM Parameters Using Chaos Optimization Algorithms

支持向量机(SVM)的参数取值决定了其学习性能和泛化能力.对此,将SVM参数的选取看作参数的组合优化,建立组合优化的目标函数,采用变尺度混沌优化算法来搜索最优目标函数值.混沌优化算法是一种全局搜索方法,在选取SVM参数时,不必考虑模型的复杂度和变量维数.仿真表明,混沌优化算法是选取SVM参数的有效方法,应用到函数逼近时具有优良的性能.

Approporiate parameters are very crucial to support vector machines （SVM） learning results and generalization ability. The selection problem of SVM parameters is considered as a compound optimization problem. Then objective function of optimization problem is set and a mutative scale chaos optimization algorithm is employed to search optimal objective function. Chaos optimization algorithm is global search method and it need not to consider SVM dimensionality and complexity. Simulations show that the proposed method is an effective approach for parameter selection and the good performance for function approximation is obtained.