Noise robustness enhancement using fourth-order cumulants cost function

C. T. Leung; T. W S Chow

doi:10.1109/ICNN.1996.549194

Noise robustness enhancement using fourth-order cumulants cost function

C. T. Leung^*, T. W S Chow

^*Corresponding author for this work

Department of Electrical Engineering

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

3 Citations (Scopus)

Abstract

A novel robust fourth-order cumulants cost function is introduced to enhance the fitting to underlying function in small data sets with high noise level of Gaussian noise. The neural network learns based on gradient descent optimization method by introducing a constraint term in the cost function. The proposed cost function was applied to benchmark sunspot series prediction and nonlinear system identification. Excellent results are obtained. The neural network can provide lower training error and excellent generalization property. Our proposed cost function enables the network to provide, at most, 73% reduction of normalized test error in the benchmark test. © 1996 IEEE

Original language	English
Title of host publication	Proceedings of International Conference on Neural Networks (ICNN'96)
Publisher	IEEE
Pages	1918-1923
Volume	4
ISBN (Print)	0-7803-3210-5
DOIs	https://doi.org/10.1109/ICNN.1996.549194
Publication status	Published - Jun 1996
Event	Proceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4) - Washington, DC, USA Duration: 3 Jun 1996 → 6 Jun 1996

Conference

Conference	Proceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4)
City	Washington, DC, USA
Period	3/06/96 → 6/06/96

Access Output

10.1109/ICNN.1996.549194

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{7702c8116741450e874f1122700470d1,

title = "Noise robustness enhancement using fourth-order cumulants cost function",

abstract = "A novel robust fourth-order cumulants cost function is introduced to enhance the fitting to underlying function in small data sets with high noise level of Gaussian noise. The neural network learns based on gradient descent optimization method by introducing a constraint term in the cost function. The proposed cost function was applied to benchmark sunspot series prediction and nonlinear system identification. Excellent results are obtained. The neural network can provide lower training error and excellent generalization property. Our proposed cost function enables the network to provide, at most, 73% reduction of normalized test error in the benchmark test. {\textcopyright} 1996 IEEE",

author = "Leung, {C. T.} and Chow, {T. W S}",

year = "1996",

month = jun,

doi = "10.1109/ICNN.1996.549194",

language = "English",

isbn = "0-7803-3210-5",

volume = "4",

pages = "1918--1923",

booktitle = "Proceedings of International Conference on Neural Networks (ICNN'96)",

publisher = "IEEE",

address = "United States",

note = "Proceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4) ; Conference date: 03-06-1996 Through 06-06-1996",

}

TY - GEN

T1 - Noise robustness enhancement using fourth-order cumulants cost function

AU - Leung, C. T.

AU - Chow, T. W S

PY - 1996/6

Y1 - 1996/6

N2 - A novel robust fourth-order cumulants cost function is introduced to enhance the fitting to underlying function in small data sets with high noise level of Gaussian noise. The neural network learns based on gradient descent optimization method by introducing a constraint term in the cost function. The proposed cost function was applied to benchmark sunspot series prediction and nonlinear system identification. Excellent results are obtained. The neural network can provide lower training error and excellent generalization property. Our proposed cost function enables the network to provide, at most, 73% reduction of normalized test error in the benchmark test. © 1996 IEEE

AB - A novel robust fourth-order cumulants cost function is introduced to enhance the fitting to underlying function in small data sets with high noise level of Gaussian noise. The neural network learns based on gradient descent optimization method by introducing a constraint term in the cost function. The proposed cost function was applied to benchmark sunspot series prediction and nonlinear system identification. Excellent results are obtained. The neural network can provide lower training error and excellent generalization property. Our proposed cost function enables the network to provide, at most, 73% reduction of normalized test error in the benchmark test. © 1996 IEEE

UR - http://www.scopus.com/inward/record.url?scp=0029768208&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-0029768208&origin=recordpage

U2 - 10.1109/ICNN.1996.549194

DO - 10.1109/ICNN.1996.549194

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 0-7803-3210-5

VL - 4

SP - 1918

EP - 1923

BT - Proceedings of International Conference on Neural Networks (ICNN'96)

PB - IEEE

T2 - Proceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4)

Y2 - 3 June 1996 through 6 June 1996

ER -

Noise robustness enhancement using fourth-order cumulants cost function

Abstract

Conference

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this