Local generalization error based monotonic classification extreme learning machine

Hong ZHU; Eric C.C. TSANG; Xizhao WANG

doi:10.1109/ICWAPR.2017.8076666

Local generalization error based monotonic classification extreme learning machine

Hong ZHU, Eric C.C. TSANG, Xizhao WANG

Research output: Book Chapters | Papers in Conference Proceedings › Conference paper (refereed) › Referred Conference Paper › peer-review

Abstract

The monotonic classification problem is a special case of classification problems, where both the condition attributes and the decision attribute are ordered, and monotonicity relationships existed between them. Based on extreme learning machine, monotonic extreme learning was proposed to solve monotonic classification problems. To improve its generalization capability, in this paper a novel algorithm is proposed based on the local generalization error model, where except for the training error, the objective function takes the sensitivity of the output with respect to the inputs' perturbations into account. An example is conducted to illustrate the feasibility and efficiency of the newly proposed algorithm.

Original language	English
Title of host publication	Proceedings of 2017 International Conference on Wavelet Analysis and Pattern Recognition, ICWAPR 2017
Publisher	IEEE
Pages	72-77
Number of pages	6
Volume	1
ISBN (Electronic)	9781538604106
DOIs	https://doi.org/10.1109/ICWAPR.2017.8076666
Publication status	Published - Jul 2017
Externally published	Yes
Event	2017 International Conference on Wavelet Analysis and Pattern Recognition, ICWAPR 2017 - Ningbo, China Duration: 9 Jul 2017 → 12 Jul 2017

Publication series

Name	International Conference on Wavelet Analysis and Pattern Recognition
Volume	1
ISSN (Print)	2158-5695
ISSN (Electronic)	2158-5709

Conference

Conference	2017 International Conference on Wavelet Analysis and Pattern Recognition, ICWAPR 2017
Country/Territory	China
City	Ningbo
Period	9/07/17 → 12/07/17

Keywords

Extreme learning machine
Generalization capability
Local generalization error
Monotonic classification
Quadratic programming

Access to Document

10.1109/ICWAPR.2017.8076666

Cite this

ZHU, H., TSANG, E. C. C., & WANG, X. (2017). Local generalization error based monotonic classification extreme learning machine. In Proceedings of 2017 International Conference on Wavelet Analysis and Pattern Recognition, ICWAPR 2017 (Vol. 1, pp. 72-77). Article 8076666 (International Conference on Wavelet Analysis and Pattern Recognition; Vol. 1). IEEE. https://doi.org/10.1109/ICWAPR.2017.8076666

@inproceedings{95855605b9ee4f078dadcf7ec7dda16d,

title = "Local generalization error based monotonic classification extreme learning machine",

abstract = "The monotonic classification problem is a special case of classification problems, where both the condition attributes and the decision attribute are ordered, and monotonicity relationships existed between them. Based on extreme learning machine, monotonic extreme learning was proposed to solve monotonic classification problems. To improve its generalization capability, in this paper a novel algorithm is proposed based on the local generalization error model, where except for the training error, the objective function takes the sensitivity of the output with respect to the inputs' perturbations into account. An example is conducted to illustrate the feasibility and efficiency of the newly proposed algorithm.",

keywords = "Extreme learning machine, Generalization capability, Local generalization error, Monotonic classification, Quadratic programming",

author = "Hong ZHU and TSANG, {Eric C.C.} and Xizhao WANG",

year = "2017",

month = jul,

doi = "10.1109/ICWAPR.2017.8076666",

language = "English",

volume = "1",

series = "International Conference on Wavelet Analysis and Pattern Recognition",

publisher = "IEEE",

pages = "72--77",

booktitle = "Proceedings of 2017 International Conference on Wavelet Analysis and Pattern Recognition, ICWAPR 2017",

note = "2017 International Conference on Wavelet Analysis and Pattern Recognition, ICWAPR 2017 ; Conference date: 09-07-2017 Through 12-07-2017",

}

ZHU, H, TSANG, ECC & WANG, X 2017, Local generalization error based monotonic classification extreme learning machine. in Proceedings of 2017 International Conference on Wavelet Analysis and Pattern Recognition, ICWAPR 2017. vol. 1, 8076666, International Conference on Wavelet Analysis and Pattern Recognition, vol. 1, IEEE, pp. 72-77, 2017 International Conference on Wavelet Analysis and Pattern Recognition, ICWAPR 2017, Ningbo, China, 9/07/17. https://doi.org/10.1109/ICWAPR.2017.8076666

Local generalization error based monotonic classification extreme learning machine. / ZHU, Hong; TSANG, Eric C.C.; WANG, Xizhao.
Proceedings of 2017 International Conference on Wavelet Analysis and Pattern Recognition, ICWAPR 2017. Vol. 1 IEEE, 2017. p. 72-77 8076666 (International Conference on Wavelet Analysis and Pattern Recognition; Vol. 1).

Research output: Book Chapters | Papers in Conference Proceedings › Conference paper (refereed) › Referred Conference Paper › peer-review

TY - GEN

T1 - Local generalization error based monotonic classification extreme learning machine

AU - ZHU, Hong

AU - TSANG, Eric C.C.

AU - WANG, Xizhao

PY - 2017/7

Y1 - 2017/7

N2 - The monotonic classification problem is a special case of classification problems, where both the condition attributes and the decision attribute are ordered, and monotonicity relationships existed between them. Based on extreme learning machine, monotonic extreme learning was proposed to solve monotonic classification problems. To improve its generalization capability, in this paper a novel algorithm is proposed based on the local generalization error model, where except for the training error, the objective function takes the sensitivity of the output with respect to the inputs' perturbations into account. An example is conducted to illustrate the feasibility and efficiency of the newly proposed algorithm.

AB - The monotonic classification problem is a special case of classification problems, where both the condition attributes and the decision attribute are ordered, and monotonicity relationships existed between them. Based on extreme learning machine, monotonic extreme learning was proposed to solve monotonic classification problems. To improve its generalization capability, in this paper a novel algorithm is proposed based on the local generalization error model, where except for the training error, the objective function takes the sensitivity of the output with respect to the inputs' perturbations into account. An example is conducted to illustrate the feasibility and efficiency of the newly proposed algorithm.

KW - Extreme learning machine

KW - Generalization capability

KW - Local generalization error

KW - Monotonic classification

KW - Quadratic programming

UR - http://www.scopus.com/inward/record.url?scp=85036452411&partnerID=8YFLogxK

U2 - 10.1109/ICWAPR.2017.8076666

DO - 10.1109/ICWAPR.2017.8076666

M3 - Conference paper (refereed)

AN - SCOPUS:85036452411

VL - 1

T3 - International Conference on Wavelet Analysis and Pattern Recognition

SP - 72

EP - 77

BT - Proceedings of 2017 International Conference on Wavelet Analysis and Pattern Recognition, ICWAPR 2017

PB - IEEE

T2 - 2017 International Conference on Wavelet Analysis and Pattern Recognition, ICWAPR 2017

Y2 - 9 July 2017 through 12 July 2017

ER -

Local generalization error based monotonic classification extreme learning machine

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this