An unsupervised parameter learning model for RVFL neural network

Zhang, Y; Wu, J; Cai, Z; Du, B; Yu, PS

An unsupervised parameter learning model for RVFL neural network

Zhang, Y Wu, J

Cai, Z Du, B Yu, PS

Permalink

Publication Type:: Journal Article
Citation:: Neural Networks, 2019, 112 pp. 85 - 97
Issue Date:: 2019-04-01

Closed Access

	Filename	Description	Size
	An unsupervised parameter learning model for RVFL neural network.pdf	Published Version	882.09 kB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Zhang, Y	en_US
dc.contributor.author	Wu, J https://orcid.org/0000-0002-1371-5801	en_US
dc.contributor.author	Cai, Z	en_US
dc.contributor.author	Du, B	en_US
dc.contributor.author	Yu, PS	en_US
dc.date.available	2019-01-18	en_US
dc.date.issued	2019-04-01	en_US
dc.identifier.citation	Neural Networks, 2019, 112 pp. 85 - 97	en_US
dc.identifier.issn	0893-6080	en_US
dc.identifier.uri	http://hdl.handle.net/10453/134869
dc.description.abstract	© 2019 Elsevier Ltd With the direct input–output connections, a random vector functional link (RVFL) network is a simple and effective learning algorithm for single-hidden layer feedforward neural networks (SLFNs). RVFL is a universal approximator for continuous functions on compact sets with fast learning property. Owing to its simplicity and effectiveness, RVFL has attracted significant interest in numerous real-world applications. In reality, the performance of RVFL is often challenged by randomly assigned network parameters. In this paper, we propose a novel unsupervised network parameter learning method for RVFL, named sparse pre-trained random vector functional link (SP-RVFL for short) network. The proposed SP-RVFL uses a sparse autoencoder with ℓ 1 -norm regularization to adaptively learn superior network parameters for specific learning tasks. By doing so, the learned network parameters in SP-RVFL are embedded with the valuable information of input data, which alleviate the randomly generated parameter issue and improve the algorithmic performance. Experiments and comparisons on 16 diverse benchmarks from different domains confirm the effectiveness of the proposed SP-RVFL. The corresponding results also demonstrate that RVFL outperforms extreme learning machine (ELM).	en_US
dc.relation.ispartof	Neural Networks	en_US
dc.relation.isbasedon	10.1016/j.neunet.2019.01.007	en_US
dc.subject.classification	Artificial Intelligence & Image Processing	en_US
dc.subject.mesh	Algorithms	en_US
dc.subject.mesh	Neural Networks (Computer)	en_US
dc.subject.mesh	Machine Learning	en_US
dc.subject.mesh	Neural Networks, Computer	en_US
dc.title	An unsupervised parameter learning model for RVFL neural network	en_US
dc.type	Journal Article
utslib.citation.volume	112	en_US
utslib.for	0801 Artificial Intelligence and Image Processing	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Computer Science
pubs.organisational-group	/University of Technology Sydney/Strength - CAI - Centre for Artificial Intelligence
utslib.copyright.status	closed_access
pubs.publication-status	Published	en_US
pubs.volume	112	en_US

Abstract:

© 2019 Elsevier Ltd With the direct input–output connections, a random vector functional link (RVFL) network is a simple and effective learning algorithm for single-hidden layer feedforward neural networks (SLFNs). RVFL is a universal approximator for continuous functions on compact sets with fast learning property. Owing to its simplicity and effectiveness, RVFL has attracted significant interest in numerous real-world applications. In reality, the performance of RVFL is often challenged by randomly assigned network parameters. In this paper, we propose a novel unsupervised network parameter learning method for RVFL, named sparse pre-trained random vector functional link (SP-RVFL for short) network. The proposed SP-RVFL uses a sparse autoencoder with ℓ 1 -norm regularization to adaptively learn superior network parameters for specific learning tasks. By doing so, the learned network parameters in SP-RVFL are embedded with the valuable information of input data, which alleviate the randomly generated parameter issue and improve the algorithmic performance. Experiments and comparisons on 16 diverse benchmarks from different domains confirm the effectiveness of the proposed SP-RVFL. The corresponding results also demonstrate that RVFL outperforms extreme learning machine (ELM).

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/134869