On the Objective Function and Learning Algorithm for Concurrent Open Node Fault

Chi Sing Leung; Pui Fai Sum; Kai-Tat Ng

doi:10.1007/978-3-642-34487-9_26

On the Objective Function and Learning Algorithm for Concurrent Open Node Fault

Chi Sing Leung, Pui Fai Sum, Kai-Tat Ng

Department of Electrical Engineering

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 12 - Chapter in an edited book (Author) › peer-review

1 Citation (Scopus)

Abstract

This paper studies the performance of faulty RBF networks when stuck-at-zero node fault and stuck-at-one node fault happen. An objective function for training fault tolerant RBF networks for node fault is first derived. A training learning algorithm for faulty RBF networks is then presented. Finally, a mean prediction error formula which can estimate the test set error of faulty networks is derived. Simulation experiments are then performed to verify our theoretical result.

Original language	English
Title of host publication	Neural Information Processing
Subtitle of host publication	19th International Conference, ICONIP 2012, Proceedings
Editors	Tingwen Huang, Zhigang Zeng, Chuandong Li, Chi Sing Leung
Place of Publication	New York
Publisher	Springer
Pages	208-216
Volume	Part III
ISBN (Electronic)	9783642344879, 3642344879
ISBN (Print)	9783642344862
DOIs	https://doi.org/10.1007/978-3-642-34487-9_26
Publication status	Published - Nov 2012
Event	19th International Conference on Neural Information Processing (ICONIP 2012) - Doha, Qatar Duration: 12 Nov 2012 → 15 Nov 2012

Publication series

Name	Lecture Notes in Computer Science
Volume	7665
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	19th International Conference on Neural Information Processing (ICONIP 2012)
Country/Territory	Qatar
City	Doha
Period	12/11/12 → 15/11/12

Research Keywords

Fault tolerance
generalization ability
RBF networks

Access Output

10.1007/978-3-642-34487-9_26

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Leung, C. S., Sum, P. F., & Ng, K.-T. (2012). On the Objective Function and Learning Algorithm for Concurrent Open Node Fault. In T. Huang, Z. Zeng, C. Li, & C. S. Leung (Eds.), Neural Information Processing: 19th International Conference, ICONIP 2012, Proceedings (Vol. Part III, pp. 208-216). (Lecture Notes in Computer Science; Vol. 7665). Springer . https://doi.org/10.1007/978-3-642-34487-9_26

Leung, Chi Sing ; Sum, Pui Fai ; Ng, Kai-Tat. / On the Objective Function and Learning Algorithm for Concurrent Open Node Fault. Neural Information Processing: 19th International Conference, ICONIP 2012, Proceedings. editor / Tingwen Huang ; Zhigang Zeng ; Chuandong Li ; Chi Sing Leung. Vol. Part III New York : Springer , 2012. pp. 208-216 (Lecture Notes in Computer Science).

@inbook{5c2e7e6b884c40fcb0eb2e40a357de3b,

title = "On the Objective Function and Learning Algorithm for Concurrent Open Node Fault",

abstract = "This paper studies the performance of faulty RBF networks when stuck-at-zero node fault and stuck-at-one node fault happen. An objective function for training fault tolerant RBF networks for node fault is first derived. A training learning algorithm for faulty RBF networks is then presented. Finally, a mean prediction error formula which can estimate the test set error of faulty networks is derived. Simulation experiments are then performed to verify our theoretical result.",

keywords = "Fault tolerance, generalization ability, RBF networks",

author = "Leung, {Chi Sing} and Sum, {Pui Fai} and Kai-Tat Ng",

year = "2012",

month = nov,

doi = "10.1007/978-3-642-34487-9_26",

language = "English",

isbn = "9783642344862",

volume = "Part III",

series = "Lecture Notes in Computer Science",

publisher = "Springer ",

pages = "208--216",

editor = "Tingwen Huang and Zhigang Zeng and Chuandong Li and Leung, {Chi Sing}",

booktitle = "Neural Information Processing",

note = "19th International Conference on Neural Information Processing (ICONIP 2012) ; Conference date: 12-11-2012 Through 15-11-2012",

}

Leung, CS, Sum, PF & Ng, K-T 2012, On the Objective Function and Learning Algorithm for Concurrent Open Node Fault. in T Huang, Z Zeng, C Li & CS Leung (eds), Neural Information Processing: 19th International Conference, ICONIP 2012, Proceedings. vol. Part III, Lecture Notes in Computer Science, vol. 7665, Springer , New York, pp. 208-216, 19th International Conference on Neural Information Processing (ICONIP 2012), Doha, Qatar, 12/11/12. https://doi.org/10.1007/978-3-642-34487-9_26

On the Objective Function and Learning Algorithm for Concurrent Open Node Fault. / Leung, Chi Sing; Sum, Pui Fai; Ng, Kai-Tat.
Neural Information Processing: 19th International Conference, ICONIP 2012, Proceedings. ed. / Tingwen Huang; Zhigang Zeng; Chuandong Li; Chi Sing Leung. Vol. Part III New York: Springer , 2012. p. 208-216 (Lecture Notes in Computer Science; Vol. 7665).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 12 - Chapter in an edited book (Author) › peer-review

TY - CHAP

T1 - On the Objective Function and Learning Algorithm for Concurrent Open Node Fault

AU - Leung, Chi Sing

AU - Sum, Pui Fai

AU - Ng, Kai-Tat

PY - 2012/11

Y1 - 2012/11

N2 - This paper studies the performance of faulty RBF networks when stuck-at-zero node fault and stuck-at-one node fault happen. An objective function for training fault tolerant RBF networks for node fault is first derived. A training learning algorithm for faulty RBF networks is then presented. Finally, a mean prediction error formula which can estimate the test set error of faulty networks is derived. Simulation experiments are then performed to verify our theoretical result.

AB - This paper studies the performance of faulty RBF networks when stuck-at-zero node fault and stuck-at-one node fault happen. An objective function for training fault tolerant RBF networks for node fault is first derived. A training learning algorithm for faulty RBF networks is then presented. Finally, a mean prediction error formula which can estimate the test set error of faulty networks is derived. Simulation experiments are then performed to verify our theoretical result.

KW - Fault tolerance

KW - generalization ability

KW - RBF networks

UR - http://www.scopus.com/inward/record.url?scp=84869002361&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-84869002361&origin=recordpage

U2 - 10.1007/978-3-642-34487-9_26

DO - 10.1007/978-3-642-34487-9_26

M3 - RGC 12 - Chapter in an edited book (Author)

SN - 9783642344862

VL - Part III

T3 - Lecture Notes in Computer Science

SP - 208

EP - 216

BT - Neural Information Processing

A2 - Huang, Tingwen

A2 - Zeng, Zhigang

A2 - Li, Chuandong

A2 - Leung, Chi Sing

PB - Springer

CY - New York

T2 - 19th International Conference on Neural Information Processing (ICONIP 2012)

Y2 - 12 November 2012 through 15 November 2012

ER -

On the Objective Function and Learning Algorithm for Concurrent Open Node Fault

Abstract

Publication series

Conference

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this