基于抗白噪声理论的支持向量机

Support Vector Machine Base on Decrese White Noise Theory

支持向量机(SVM)是在统计学习理论基础上发展起来的一种新的机器学习方法.具有泛化能力强,全局最优等特点.我们针对于传统的支持向量机算法忽略了当采取的训练集中有噪声干扰的情况,通过改造原有的经验风险和调节核函数中的参数,达到抑制或者减弱随机噪声干扰的目的,并具体地给出了抗高斯白噪声的支持向量机模型.

Support Vector Machine（SVM） based on the statistical learning theory is a machine learning because of its advantage such as firm mathematic theory foundation,strict theory analysis,complete theory,globel optimization as well as good adaptability and genenalization.For the traditional algorithms of Support Vector Machine neglected when training group is interfered with noise.we can resolve by transforming the experience risk measurement of the original Support Vector Machine algorithm or adjusting the parameters of kernel function.Then,we can control or decrease the random noise.At last,there is a concrete model that control White Gaussian Noise is geven.