Incremental extreme learning machine

This new theory shows that in order to let SLFNs work as universal approximators, one may simply randomly choose input-to-hidden nodes, and then we only need to adjust the output weights linking the hidden layer and the output layer. In such SLFNs implementations, the activation functions for additi...

Full description

Saved in:

Bibliographic Details
Main Author:	Chen, Lei
Other Authors:	Huang Guangbin
Format:	Theses and Dissertations
Published:	2008
Subjects:	DRNTU::Engineering::Electrical and electronic engineering::Computer hardware, software and systems
Online Access:	https://hdl.handle.net/10356/3804
Tags:	Add Tag No Tags, Be the first to tag this record!
Institution:	Nanyang Technological University

id	sg-ntu-dr.10356-3804
record_format	dspace
spelling	sg-ntu-dr.10356-38042023-07-04T17:12:41Z Incremental extreme learning machine Chen, Lei Huang Guangbin School of Electrical and Electronic Engineering DRNTU::Engineering::Electrical and electronic engineering::Computer hardware, software and systems This new theory shows that in order to let SLFNs work as universal approximators, one may simply randomly choose input-to-hidden nodes, and then we only need to adjust the output weights linking the hidden layer and the output layer. In such SLFNs implementations, the activation functions for additive nodes can be any bounded nonconstant piecewise continuous functions or the activation functions for RBF nodes can be any integrable piecewise continuous functions.We propose two incremental algorithms:1) Incremental extreme learning machine (I-ELM) 2) Convex I-ELM (CI-ELM). DOCTOR OF PHILOSOPHY (EEE) 2008-09-17T09:37:53Z 2008-09-17T09:37:53Z 2007 2007 Thesis Chen, L. (2007). Incremental extreme learning machine. Doctoral thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/3804 10.32657/10356/3804 Nanyang Technological University application/pdf
institution	Nanyang Technological University
building	NTU Library
continent	Asia
country	Singapore Singapore
content_provider	NTU Library
collection	DR-NTU
topic	DRNTU::Engineering::Electrical and electronic engineering::Computer hardware, software and systems
spellingShingle	DRNTU::Engineering::Electrical and electronic engineering::Computer hardware, software and systems Chen, Lei Incremental extreme learning machine
description	This new theory shows that in order to let SLFNs work as universal approximators, one may simply randomly choose input-to-hidden nodes, and then we only need to adjust the output weights linking the hidden layer and the output layer. In such SLFNs implementations, the activation functions for additive nodes can be any bounded nonconstant piecewise continuous functions or the activation functions for RBF nodes can be any integrable piecewise continuous functions.We propose two incremental algorithms:1) Incremental extreme learning machine (I-ELM) 2) Convex I-ELM (CI-ELM).
author2	Huang Guangbin
author_facet	Huang Guangbin Chen, Lei
format	Theses and Dissertations
author	Chen, Lei
author_sort	Chen, Lei
title	Incremental extreme learning machine
title_short	Incremental extreme learning machine
title_full	Incremental extreme learning machine
title_fullStr	Incremental extreme learning machine
title_full_unstemmed	Incremental extreme learning machine
title_sort	incremental extreme learning machine
publishDate	2008
url	https://hdl.handle.net/10356/3804
_version_	1772827212081266688

Incremental extreme learning machine

Similar Items