一种基于簇的极限学习机的在线学习算法  

Clustering_based and ELM_based online learning algorithm

作　　者：张敏[1] 曾新苗 马长春[1] 

机构地区：[1]重庆大学计算机学院,重庆400030

出　　处：《计算机工程与应用》2014年第11期188-191,266,共5页Computer Engineering and Applications

基　　金：重庆市科委自然科学基金(No.CSTC2011BB2063)

摘　　要：针对传统的批量学习算法学习速度慢、对空间需求量高的缺点,提出了一种基于簇的极限学习机的在线学习算法。该算法将分簇的理念融入到极限学习机中,并结合极限学习机,提出了一种基于样本类别和样本输出的分簇标准;同时提出了一种加权的Moore-Penrose算法求隐层节点与输出节点的连接权重。实验结果表明,该算法具有学习能力好、拟合度高、泛化性能好等优点。Traditional batch learning algorithm is slow to learn and has a high demand for space. This paper proposes a clutering_based and ELM_based online learning algorithm. In this algorithm, it takes the concept of clustering into extreme learning machine, combines with extreme learning machine, proposes a category_based, output_based standard of clustering. At the same time, it also proposes a weighted Moore-Penrose algorithm to solve the weight vector connecting the hidden nodes and the output nodes. The result shows that this algorithm has good learning ability and high goodness of fit, pro-duces better generalization performance, and so on.

关 键 词：极限学习机 簇 在线学习 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]