Double robustness analysis for determining optimal feedforward neural network architecture

Lean Yu; Kin Keung Lai; Shouyang Wang

doi:10.1007/11539087_48

Double robustness analysis for determining optimal feedforward neural network architecture

Lean Yu
, Kin Keung Lai
, Shouyang Wang

Department of Decision Analytics and Operations

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

2 Citations (Scopus)

Abstract

This paper incorporates robustness into neural network modeling and proposes a novel two-phase robustness analysis approach for determining the optimal feedforward neural network (FNN) architecture in terms of Hellinger distance of probability density function (PDF) of error distribution. The proposed approach is illustrated with an example in this paper. © Springer-Verlag Berlin Heidelberg 2005.

Original language	English
Title of host publication	Advances in Natural Computation
Subtitle of host publication	First International Conference, ICNC 2005, Changsha, China, August 27-29, 2005, Proceedings, Part I
Place of Publication	Berlin, Heidelberg
Publisher	Springer
Pages	382-385
ISBN (Electronic)	978-3-540-31853-8
ISBN (Print)	978-3-540-28323-2
DOIs	https://doi.org/10.1007/11539087_48
Publication status	Published - 2005
Event	1st International Conference on Natural Computation (ICNC 2005) - Changsha, China Duration: 27 Aug 2005 → 29 Aug 2005

Publication series

Name	Lecture Notes in Computer Science
Volume	3610
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	1st International Conference on Natural Computation (ICNC 2005)
Place	China
City	Changsha
Period	27/08/05 → 29/08/05

Access Output

10.1007/11539087_48

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Yu, L., Lai, K. K., & Wang, S. (2005). Double robustness analysis for determining optimal feedforward neural network architecture. In Advances in Natural Computation: First International Conference, ICNC 2005, Changsha, China, August 27-29, 2005, Proceedings, Part I (pp. 382-385). (Lecture Notes in Computer Science; Vol. 3610). Springer . https://doi.org/10.1007/11539087_48

@inproceedings{c0d1238d0bdc4d17ac77901b2bb83e78,

title = "Double robustness analysis for determining optimal feedforward neural network architecture",

abstract = "This paper incorporates robustness into neural network modeling and proposes a novel two-phase robustness analysis approach for determining the optimal feedforward neural network (FNN) architecture in terms of Hellinger distance of probability density function (PDF) of error distribution. The proposed approach is illustrated with an example in this paper. {\textcopyright} Springer-Verlag Berlin Heidelberg 2005.",

author = "Lean Yu and Lai, \{Kin Keung\} and Shouyang Wang",

year = "2005",

doi = "10.1007/11539087\_48",

language = "English",

isbn = "978-3-540-28323-2",

series = "Lecture Notes in Computer Science",

publisher = "Springer ",

pages = "382--385",

booktitle = "Advances in Natural Computation",

note = "1st International Conference on Natural Computation (ICNC 2005) ; Conference date: 27-08-2005 Through 29-08-2005",

}

Yu, L, Lai, KK & Wang, S 2005, Double robustness analysis for determining optimal feedforward neural network architecture. in Advances in Natural Computation: First International Conference, ICNC 2005, Changsha, China, August 27-29, 2005, Proceedings, Part I. Lecture Notes in Computer Science, vol. 3610, Springer , Berlin, Heidelberg, pp. 382-385, 1st International Conference on Natural Computation (ICNC 2005), Changsha, China, 27/08/05. https://doi.org/10.1007/11539087_48

Double robustness analysis for determining optimal feedforward neural network architecture. / Yu, Lean; Lai, Kin Keung; Wang, Shouyang.
Advances in Natural Computation: First International Conference, ICNC 2005, Changsha, China, August 27-29, 2005, Proceedings, Part I. Berlin, Heidelberg: Springer , 2005. p. 382-385 (Lecture Notes in Computer Science; Vol. 3610).

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

TY - GEN

T1 - Double robustness analysis for determining optimal feedforward neural network architecture

AU - Yu, Lean

AU - Lai, Kin Keung

AU - Wang, Shouyang

PY - 2005

Y1 - 2005

N2 - This paper incorporates robustness into neural network modeling and proposes a novel two-phase robustness analysis approach for determining the optimal feedforward neural network (FNN) architecture in terms of Hellinger distance of probability density function (PDF) of error distribution. The proposed approach is illustrated with an example in this paper. © Springer-Verlag Berlin Heidelberg 2005.

AB - This paper incorporates robustness into neural network modeling and proposes a novel two-phase robustness analysis approach for determining the optimal feedforward neural network (FNN) architecture in terms of Hellinger distance of probability density function (PDF) of error distribution. The proposed approach is illustrated with an example in this paper. © Springer-Verlag Berlin Heidelberg 2005.

UR - https://www.scopus.com/pages/publications/26844544084

UR - https://www.scopus.com/pages/publications/26844544084#tab=impact

U2 - 10.1007/11539087_48

DO - 10.1007/11539087_48

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

SN - 978-3-540-28323-2

T3 - Lecture Notes in Computer Science

SP - 382

EP - 385

BT - Advances in Natural Computation

PB - Springer

CY - Berlin, Heidelberg

T2 - 1st International Conference on Natural Computation (ICNC 2005)

Y2 - 27 August 2005 through 29 August 2005

ER -

Yu L, Lai KK, Wang S. Double robustness analysis for determining optimal feedforward neural network architecture. In Advances in Natural Computation: First International Conference, ICNC 2005, Changsha, China, August 27-29, 2005, Proceedings, Part I. Berlin, Heidelberg: Springer . 2005. p. 382-385. (Lecture Notes in Computer Science). Epub 2005 Aug 25. doi: 10.1007/11539087_48

Double robustness analysis for determining optimal feedforward neural network architecture

Abstract

Publication series

Conference

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this