关键词: 支持向量机 最小二乘支持向量机 特征维数增量学习

Abstract:

In order to tackle with the incremental learning problems with new features, an incremental feature learning algorithm for the least square support ve ctor machine is proposed in this paper. In this algorithm, using historic structural parameters trained from the already existing features, the algorithm only trains the new features with the least square support vector machine Experiments show that this algorithm has two outstanding properties. First, different kernel functions can be used for the already existing features and the new features according to the distribution of samples. Second, the trai ning time and the memory space can be reduced. Some UCI datasets are used to demonstrate the less training time or the better performance of this algori  thm than the standard least square support vector machine.

Key words: support vector machine;least square support vector machine, feature dimension incremental learning