基于SVM的新多类分类算法

给出了一种基于编码二叉树的支持向量的多类分类算法.先定义了一种构造编码二叉树的方法,在此基础上合理的使用每个训练样本对应的编码来对多类样本进行划分,使之转化为两类分类问题.可以看出该算法可以大大减少子分类器的构造个数,从而简化了多类SVM分类算法.

New Multi-category Classification Algorithm Based on SVM

Produce an algorithm based on encoding binary tree and supporting vector multi-category classification algorithm.First a method of making encoding binary tree is defined,second using reasonably every training samples corresponding to the code to divide multi-category samples based on this and turn them into two classifications.It can be seen that the algorithm can greatly reduce the number of sub-classification structure,which simplifies Multi-category SVM classification algorithm.