Improvements on parsimonious extreme learning machine using recursive orthogonal least squares

详细信息    查看全文

• 作者：Yong-Ping Zhaop>ap>p> ; p>p>y.p.zhao@163.com" class="auth_mail" title="E-mail the corresponding authorp>p> ; p>p>y.p.zhao@nuaa.edu.cn" class="auth_mail" title="E-mail the corresponding authorp>Author Vitae ; Ramó ; n Huertap>bp>Author Vitae
• 关键词：Single-hidden-layer feedforward network ; Extreme learning machine ; Givens rotation ; Householder transformation
• 刊名：Neurocomputing
• 出版年：2016
• 出版时间：26 May 2016
• 年：2016
• 卷：191
• 期：Complete
• 页码：82-94
• 全文大小：562 K

文摘

Recently novel constructive and destructive parsimonious extreme learning machines (CP-ELM and DP-ELM) arose to cope with regression problems. With these foundations, several improvements on CP-ELM and DP-ELM are suggested. CP-ELM can be improved by replacing the Givens rotation with the Householder transformation, yielding the improved CP-ELM (ICP-ELM) which results in the acceleration of the training speed without hampering the generalization performance. Subsequently, a hybrid constructive–destructive ELM (CDP-ELM) is generated integrating elements from CP-ELM and DP-ELM. The goal is to combine the advantages of training speed and parsimony from CP-ELM and DP-ELM. Finally, experiments on regression data sets and a real-world system identification of robot arm example are done to test the feasibility and efficacy of these variants including ICP-ELM and CDP-ELM.