Cover Image

Extreme learning machine for structured output spaces

Recently, extreme learning machine (ELM) has attracted increasing attention due to its successful applications in classification, regression, and ranking. Normally, the desired output of the learning system using these machine learning techniques is a simple scalar output. However, there are many ap...

Full description

Saved in:
Bibliographic Details
Main Authors: Maliha, Ayman, Yusof, Rubiyah, Shapiai, Mohd. Ibrahim
Format: Article
Published: Springer London 2016
Subjects:
T Technology (General)
Online Access:http://eprints.utm.my/id/eprint/72793/
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85006409377&doi=10.1007%2fs00521-016-2754-1&partnerID=40&md5=c1d3cfdda099203a139dc3bb9324612d
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.utm.72793
record_format eprints
spelling my.utm.727932017-11-20T07:57:23Z http://eprints.utm.my/id/eprint/72793/ Extreme learning machine for structured output spaces Maliha, Ayman Yusof, Rubiyah Shapiai, Mohd. Ibrahim T Technology (General) Recently, extreme learning machine (ELM) has attracted increasing attention due to its successful applications in classification, regression, and ranking. Normally, the desired output of the learning system using these machine learning techniques is a simple scalar output. However, there are many applications in machine learning which require more complex output rather than a simple scalar one. Therefore, structured output is used for such applications where the system is trained to predict structured output instead of simple one. Previously, support vector machine (SVM) has been introduced for structured output learning in various applications. However, from machine learning point of view, ELM is known to offer better generalization performance compared to other learning techniques. In this study, we extend ELM to more generalized framework to handle complex outputs where simple outputs are considered as special cases of it. Besides the good generalization property of ELM, the resulting model will possesses rich internal structure that reflects task-specific relations and constraints. The experimental results show that structured ELM achieves similar (for binary problems) or better (for multi-class problems) generalization performance when compared to ELM. Moreover, as verified by the simulation results, structured ELM has comparable or better precision performance with structured SVM when tested for more complex output such as object localization problem on PASCAL VOC2006. Also, the investigation on parameter selections is presented and discussed for all problems. Springer London 2016 Article PeerReviewed Maliha, Ayman and Yusof, Rubiyah and Shapiai, Mohd. Ibrahim (2016) Extreme learning machine for structured output spaces. Neural Computing and Applications . pp. 1-14. ISSN 0941-0643 (In Press) https://www.scopus.com/inward/record.uri?eid=2-s2.0-85006409377&doi=10.1007%2fs00521-016-2754-1&partnerID=40&md5=c1d3cfdda099203a139dc3bb9324612d
institution Universiti Teknologi Malaysia
building UTM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Malaysia
content_source UTM Institutional Repository
url_provider http://eprints.utm.my/
topic T Technology (General)
spellingShingle T Technology (General)
Maliha, Ayman
Yusof, Rubiyah
Shapiai, Mohd. Ibrahim
Extreme learning machine for structured output spaces
description Recently, extreme learning machine (ELM) has attracted increasing attention due to its successful applications in classification, regression, and ranking. Normally, the desired output of the learning system using these machine learning techniques is a simple scalar output. However, there are many applications in machine learning which require more complex output rather than a simple scalar one. Therefore, structured output is used for such applications where the system is trained to predict structured output instead of simple one. Previously, support vector machine (SVM) has been introduced for structured output learning in various applications. However, from machine learning point of view, ELM is known to offer better generalization performance compared to other learning techniques. In this study, we extend ELM to more generalized framework to handle complex outputs where simple outputs are considered as special cases of it. Besides the good generalization property of ELM, the resulting model will possesses rich internal structure that reflects task-specific relations and constraints. The experimental results show that structured ELM achieves similar (for binary problems) or better (for multi-class problems) generalization performance when compared to ELM. Moreover, as verified by the simulation results, structured ELM has comparable or better precision performance with structured SVM when tested for more complex output such as object localization problem on PASCAL VOC2006. Also, the investigation on parameter selections is presented and discussed for all problems.
format Article
author Maliha, Ayman
Yusof, Rubiyah
Shapiai, Mohd. Ibrahim
author_facet Maliha, Ayman
Yusof, Rubiyah
Shapiai, Mohd. Ibrahim
author_sort Maliha, Ayman
title Extreme learning machine for structured output spaces
title_short Extreme learning machine for structured output spaces
title_full Extreme learning machine for structured output spaces
title_fullStr Extreme learning machine for structured output spaces
title_full_unstemmed Extreme learning machine for structured output spaces
title_sort extreme learning machine for structured output spaces
publisher Springer London
publishDate 2016
url http://eprints.utm.my/id/eprint/72793/
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85006409377&doi=10.1007%2fs00521-016-2754-1&partnerID=40&md5=c1d3cfdda099203a139dc3bb9324612d
_version_ 1643656512356220928
score 13.251813

Similar Items