Denoising Laplacian multi-layer extreme learning machine

详细信息    查看全文

• 作者：Nan Zhang^a ; ^bAuthor Vitae ; Shifei Ding^a ; ^b ; ^c ; ^{dingsf@cumt.edu.cn" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Zhongzhi Shi^cAuthor Vitae
• 关键词：Extreme learning machine ; Semi-supervised learning ; Deep learning ; Denoising ; Manifold regularization
• 刊名：Neurocomputing
• 出版年：2016
• 出版时间：1 January 2016
• 年：2016
• 卷：171
• 期：Complete
• 页码：1066-1074
• 全文大小：926 K

文摘

Most of semi-supervised learning algorithms based on manifold regularization framework are surface learning algorithms, such as semi-supervised ELM (SS-ELM) and Laplacian smooth twin support vector machine (Lap-STSVM). Multi-layer extreme learning machine (ML-ELM) stacks extreme learning machine based auto encoder (ELM-AE) to create a multi-layer neural network. ML-ELM not only approximates the complicated function but also achieves fast training time. The outputs of ELM-AE are the same as inputs, which cannot guarantee the effectiveness of the learning feature representations. We put forward extreme learning machine based denoising auto encoder (ELM-DAE) which introduces local denoising criterion into ELM-AE and is used as the basic component for Denoising ML-ELM. Resembling ML-ELM, Denoising ML-ELM stacks ELM-DAE to create a deep network. And then we introduce manifold regularization into the model of Denoising ML-ELM and propose denoising Laplacian ML-ELM (Denoising Lap-ML-ELM). Denoising Lap-ML-ELM is more efficient than SS-ELM in classification and does not need to spend too much time. Experimental results show that Denoising ML-ELM and Denoising Lap-ML-ELM are effective learning algorithms.