Abstract: Support vector machines are successfully applied to solve a large number of classification and regression problems. But it may sometimes be preferable to learn incrementally from previous SVM results, as SVMs which involve the solution of a quadratic programming problem suffer from the problem of large memory requirement and CPU time when they are trained in batch mode on large data sets, especially on multi-class problem. An approach for incremental learning based on support vector machines is presented, and is used to solve multi-class real-world problem.

Key words: Support vector machines(SVMs), Incremental learning, Multi-class problem

摘要： 支持向量机被成功地应用在分类和回归问题中，但是由于其需要求解二次规划，使得支持向量机在求解大规模数据上具有一定的缺陷，尤其是对于多分类问题，现有的支持向量机算法具有太高的算法复杂性。该文提出一种基于支持向量机的增量学习算法，适合多分类问题，并将之用于解决实际问题。

关键词: 支持向量机, 增量学习, 多分类问题

CLC Number: 

• TP18