Generalized extreme learning machine autoencoder and a new deep neural network

详细信息    查看全文

• 作者：Kai Sun ^{kai.s@foxmail.com}Author Vitae ; Jiangshe Zhang ; ^{jszhang@mail.xjtu.edu.cn}Author Vitae ; Chunxia Zhang ^{cxzhang@mail.xjtu.edu.cn}Author Vitae ; Junying Hu ^{hujunyingmm@163.com}Author Vitae
• 关键词：Extreme learning machine ; Generalized extreme learning machine autoencoder ; Manifold regularization ; Deep neural network ; Multilayer generalized extreme learning machine autoencoder
• 刊名：Neurocomputing
• 出版年：2017
• 出版时间：22 March 2017
• 年：2017
• 卷：230
• 期：Complete
• 页码：374-381
• 全文大小：665 K
• 卷排序：230

文摘

Extreme learning machine (ELM) is an efficient learning algorithm of training single layer feed-forward neural networks (SLFNs). With the development of unsupervised learning in recent years, integrating ELM with autoencoder has become a new perspective for extracting feature using unlabeled data. In this paper, we propose a new variant of extreme learning machine autoencoder (ELM-AE) called generalized extreme learning machine autoencoder (GELM-AE) which adds the manifold regularization to the objective of ELM-AE. Some experiments carried out on real-world data sets show that GELM-AE outperforms some state-of-the-art unsupervised learning algorithms, including k-means, laplacian embedding (LE), spectral clustering (SC) and ELM-AE. Furthermore, we also propose a new deep neural network called multilayer generalized extreme learning machine autoencoder (ML-GELM) by stacking several GELM-AE to detect more abstract representations. The experiments results show that ML-GELM outperforms ELM and many other deep models, such as multilayer ELM autoencoder (ML-ELM), deep belief network (DBN) and stacked autoencoder (SAE). Due to the utilization of ELM, ML-GELM is also faster than DBN and SAE.