Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/36180
Title: A fast learning method for feedforward neural networks
Authors: Wang, ST
Chung, FL 
Wang, J
Wu, J
Keywords: Fast learning method
Feedforward neural network
Extreme learning machine
Hidden-feature-space ridge regression
Issue Date: 2015
Publisher: Elsevier
Source: Neurocomputing, 2015, v. 149, p. 295-307 How to cite?
Journal: Neurocomputing 
Abstract: In order to circumvent the weakness of very slow convergence of most traditional learning algorithms for single layer feedforward neural networks, the extreme learning machines (ELM) has been recently developed to achieve extremely fast learning with good performance by training only for the output weights. However, it cannot be applied to multiple-hidden layer feedforward neural networks (MI.FN), which is a challenging bottleneck of ELM. In this work, the novel fast learning method (KM) for feedforward neural networks is proposed. Firstly, based on the existing ridge regression theories, the hidden-feature-space ridge regression (HFSR) and centered ridge regression Centered-ELM are presented. Their connection with ELM is also theoretically revealed. As special kernel methods, they can inherently be used to propagate the prominent advantages of ELM into MU:N. Then, a novel fast learning method FLM for teedforward neural networks is proposed as a unified framework for HFSR and Centered-ELM. FLM can be applied for both SLFN and MLFN with a single or multiple outputs. In FLM, only the parameters in the last hidden layer require being adjusted while all the parameters in other hidden layers can be randomly assigned. The proposed FLM was tested against state of the art methods on real-world datasets and it provides better and more reliable results.
URI: http://hdl.handle.net/10397/36180
ISSN: 0925-2312
EISSN: 1872-8286
DOI: 10.1016/j.neucom.2014.01.065
Appears in Collections:Journal/Magazine Article

Access
View full-text via PolyU eLinks SFX Query
Show full item record

SCOPUSTM   
Citations

6
Citations as of Feb 25, 2017

WEB OF SCIENCETM
Citations

6
Last Week
0
Last month
Citations as of Jul 15, 2017

Page view(s)

26
Last Week
0
Last month
Checked on Jul 16, 2017

Google ScholarTM

Check

Altmetric



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.