欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
本文首先分析了增量学习过程中支持向量与非支持向量的相互转化问题，而后在此基础上提出了基于超球结构的支持向量机增量学习算法。该算法主要利用超球结构，完成对增量学习中训练样本的选取，进而完成分类器的重构。实验表明，该算法比传统支持向量机增量学习算法具有更高的分类精度。
英文摘要：
The transformation between support vectors and normal vectors during incremental learning is analyzed firstly. And the incremental SVM learning algorithm based on hyper-sphere structure is put forward consequently. The novel approach reconstructs SVM classifier through the selection of training samples in incremental learning with approach based on hyper-sphere structure employed. The results of experiments show that this algorithm works better than traditional SVM incremental algorithms.
同期刊论文项目
同项目期刊论文
The evolvement and relevant factors of price discovery: A case study of cross-listed stocks in China
A hybrid genetic and variable neighborhood descent algorithm for flexible job shop scheduling proble
The evolvement and relevant factors of price discovery: A case study of cross-listed stocks in China
A hybrid genetic and variable neighborhood descent algorithm for flexible job shop scheduling proble
A hybrid of genetic algorithm and bottleneck shifting for multiobjective flexible job shop schedulin
位置：