Please use this identifier to cite or link to this item: https://doi.org/10.1016/j.neucom.2007.07.025
Title: Incremental extreme learning machine with fully complex hidden nodes
Authors: Huang, G.-B.
Li, M.-B.
Chen, L. 
Siew, C.-K.
Keywords: Channel equalization
Complex activation function
Constructive networks
ELM
Feedforward networks
I-ELM
Issue Date: 2008
Source: Huang, G.-B., Li, M.-B., Chen, L., Siew, C.-K. (2008). Incremental extreme learning machine with fully complex hidden nodes. Neurocomputing 71 (4-6) : 576-583. ScholarBank@NUS Repository. https://doi.org/10.1016/j.neucom.2007.07.025
Abstract: Huang et al. [Universal approximation using incremental constructive feedforward networks with random hidden nodes, IEEE Trans. Neural Networks 17(4) (2006) 879-892] has recently proposed an incremental extreme learning machine (I-ELM), which randomly adds hidden nodes incrementally and analytically determines the output weights. Although hidden nodes are generated randomly, the network constructed by I-ELM remains as a universal approximator. This paper extends I-ELM from the real domain to the complex domain. We show that, as long as the hidden layer activation function is complex continuous discriminatory or complex bounded nonlinear piecewise continuous, I-ELM can still approximate any target functions in the complex domain. The universal capability of the I-ELM in the complex domain is further verified by two function approximations and one channel equalization problems. © 2007 Elsevier B.V. All rights reserved.
Source Title: Neurocomputing
URI: http://scholarbank.nus.edu.sg/handle/10635/39831
ISSN: 09252312
DOI: 10.1016/j.neucom.2007.07.025
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

139
checked on Dec 11, 2017

WEB OF SCIENCETM
Citations

110
checked on Dec 11, 2017

Page view(s)

54
checked on Dec 9, 2017

Google ScholarTM

Check

Altmetric


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