山东理工大学学报（自然科学版）

支持向量机(Support Vector Machine,SVM)是由Vapnik等人提出的一种基于统计学习理论的新型机器学习算法;而人工神经网络(Artificial Neural Network,ANN)已经成功用于解决模式识别和任意非线性函数回归估计问题中.介绍了支持向量机与人工神经网络的基本原理,并对二者进行了逼近方面的比较,结果表明,支持向量机作为一种新兴技术而具有的独特的优越性.

The support vector machine(SVM),put forward by some researchers and Vapnik,is a new machine learning algorithm,based theoretically on statistic learning theory.At the same time,the artificial neural network(ANN) has been successfully applied to solve problems such as mode recognition and regression of non-liner function.The paper introduces the basic theory of SVM and ANN in brief.In addition,the paper compares the approach ability of SVM and ANN,and the results indicate that SVM,as a new technique,has more superiorities.