Please use this identifier to cite or link to this item:
Title: Unsupervised feature learning with sparse Bayesian auto-encoding based extreme learning machine
Authors: Zhang, Guanghao
Cui, Dongshun
Mao, Shangbo
Huang, Guang-Bin
Keywords: Engineering::Electrical and electronic engineering
Issue Date: 2020
Source: Zhang, G., Cui, D., Mao, S. & Huang, G. (2020). Unsupervised feature learning with sparse Bayesian auto-encoding based extreme learning machine. International Journal of Machine Learning and Cybernetics, 11(7), 1557-1569.
Journal: International Journal of Machine Learning and Cybernetics
Abstract: Extreme learning machine (ELM) is a popular method in machine learning with extremely few parameters, fast learning speed and model efficiency. Unsupervised feature learning based ELM receives rising research focus. Recently the ELM auto-encoder (ELM-AE) was proposed for this task, which develops the ELM based compact feature learning without sacrificing elegant solution. Compared with ELM-AE and following ℓ1-regularized ELM-AE, we introduce a sparse Bayesian learning scheme into ELM-AE for better generalization capability. A parallel training strategy is also integrated to improve time-efficiency of multi-output sparse Bayesian learning. Furthermore, pruning hidden nodes for better performance and efficiency according to estimated variances of prior distribution of output weights is achieved. Experiments on several datasets verify the effectiveness and efficiency of our proposed ELM-AE for unsupervised feature learning, compared with PCA, NMF, ELM-AE and ℓ1-regularized ELM-AE.
ISSN: 1868-8071
DOI: 10.1007/s13042-019-01057-7
Schools: School of Electrical and Electronic Engineering 
Rights: © 2020 Springer-Verlag GmbH Germany, part of Springer Nature. All rights reserved.
Fulltext Permission: none
Fulltext Availability: No Fulltext
Appears in Collections:EEE Journal Articles

Citations 50

Updated on Sep 22, 2023

Web of ScienceTM
Citations 10

Updated on Sep 22, 2023

Page view(s)

Updated on Sep 21, 2023

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.