论文部分内容阅读
SVM是由Vapnik及其领导的AT&T Bell实验室研究小组提出的一种新的非常有发展前景的机器学习算法。本文通过它与神经网络学习算法的比较,说明了SVM具有较强的理论依据和较好的泛化性能。本文是SVM的发展综述,重点介绍了SVM的理论依据和一些值得研究的问题。
SVM is a new and promising machine learning algorithm proposed by Vapnik and its research team led by AT & T Bell Labs. In this paper, it is compared with the neural network learning algorithm to show that SVM has strong theoretical basis and good generalization performance. This article is a summary of the development of SVM, focusing on the theoretical basis of SVM and some worthy of study.