The Performance of the Stochastic DNN-kWTA Network

Ruibin Feng; Chi-Sing Leung; Kai-Tat Ng; John Sum

doi:10.1007/978-3-319-12637-1_35

The Performance of the Stochastic DNN-kWTA Network

Ruibin Feng, Chi-Sing Leung, Kai-Tat Ng, John Sum

Department of Electrical Engineering

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

Abstract

Recently, the dual neural network (DNN) model has been used to synthesize the k-winners-take-all (kWTA) process. The advantage of this DNN-kWTA model is that its structure is very simple. It contains 2n + 1 connections only. Also, the convergence behavior of the DNN-kWTA model under the noise condition was reported. However, there is no an analytic expression on the equilibrium point. Hence it is difficult to study how the noise condition affects the model performance. This paper studies how the noise condition affects the model performance. Based on the energy function, we propose an efficient method to study the performance of the DNN-kWTA model under the noise condition. Hence we can efficiently study how the noise condition affects the model performance.

Original language	English
Title of host publication	Neural Information Processing
Subtitle of host publication	21st International Conference, ICONIP 2014, Kuching, Malaysia, November 3-6, 2014: Proceedings
Editors	Chu Kiong Loo, Keem Siah Yap, Kok Wai Wong, Andrew Teoh, Kaizhu Huang
Place of Publication	Cham
Publisher	Springer
Pages	279-286
Volume	Part I
ISBN (Electronic)	9783319126371
ISBN (Print)	9783319126364
DOIs	https://doi.org/10.1007/978-3-319-12637-1_35
Publication status	Published - Nov 2014
Event	21st International Conference on Neural Information Processing (ICONIP 2014) - Kuching, Malaysia Duration: 3 Nov 2014 → 6 Nov 2014

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer
Volume	8834
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	21st International Conference on Neural Information Processing (ICONIP 2014)
Country/Territory	Malaysia
City	Kuching
Period	3/11/14 → 6/11/14

Access Output

10.1007/978-3-319-12637-1_35

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Feng, R., Leung, C.-S., Ng, K.-T., & Sum, J. (2014). The Performance of the Stochastic DNN-kWTA Network. In C. K. Loo, K. S. Yap, K. W. Wong, A. Teoh, & K. Huang (Eds.), Neural Information Processing: 21st International Conference, ICONIP 2014, Kuching, Malaysia, November 3-6, 2014: Proceedings (Vol. Part I, pp. 279-286). (Lecture Notes in Computer Science; Vol. 8834). Springer . https://doi.org/10.1007/978-3-319-12637-1_35

Feng, Ruibin ; Leung, Chi-Sing ; Ng, Kai-Tat et al. / The Performance of the Stochastic DNN-kWTA Network. Neural Information Processing: 21st International Conference, ICONIP 2014, Kuching, Malaysia, November 3-6, 2014: Proceedings. editor / Chu Kiong Loo ; Keem Siah Yap ; Kok Wai Wong ; Andrew Teoh ; Kaizhu Huang. Vol. Part I Cham : Springer , 2014. pp. 279-286 (Lecture Notes in Computer Science).

@inbook{bbc09680345d4cbfa198c128f5284827,

title = "The Performance of the Stochastic DNN-kWTA Network",

abstract = "Recently, the dual neural network (DNN) model has been used to synthesize the k-winners-take-all (kWTA) process. The advantage of this DNN-kWTA model is that its structure is very simple. It contains 2n + 1 connections only. Also, the convergence behavior of the DNN-kWTA model under the noise condition was reported. However, there is no an analytic expression on the equilibrium point. Hence it is difficult to study how the noise condition affects the model performance. This paper studies how the noise condition affects the model performance. Based on the energy function, we propose an efficient method to study the performance of the DNN-kWTA model under the noise condition. Hence we can efficiently study how the noise condition affects the model performance.",

author = "Ruibin Feng and Chi-Sing Leung and Kai-Tat Ng and John Sum",

year = "2014",

month = nov,

doi = "10.1007/978-3-319-12637-1_35",

language = "English",

isbn = "9783319126364",

volume = "Part I",

series = "Lecture Notes in Computer Science",

publisher = "Springer ",

pages = "279--286",

editor = "Loo, {Chu Kiong} and Yap, {Keem Siah} and Wong, {Kok Wai} and Andrew Teoh and Kaizhu Huang",

booktitle = "Neural Information Processing",

note = "21st International Conference on Neural Information Processing (ICONIP 2014) ; Conference date: 03-11-2014 Through 06-11-2014",

}

Feng, R, Leung, C-S, Ng, K-T & Sum, J 2014, The Performance of the Stochastic DNN-kWTA Network. in CK Loo, KS Yap, KW Wong, A Teoh & K Huang (eds), Neural Information Processing: 21st International Conference, ICONIP 2014, Kuching, Malaysia, November 3-6, 2014: Proceedings. vol. Part I, Lecture Notes in Computer Science, vol. 8834, Springer , Cham, pp. 279-286, 21st International Conference on Neural Information Processing (ICONIP 2014), Kuching, Malaysia, 3/11/14. https://doi.org/10.1007/978-3-319-12637-1_35

The Performance of the Stochastic DNN-kWTA Network. / Feng, Ruibin; Leung, Chi-Sing; Ng, Kai-Tat et al.
Neural Information Processing: 21st International Conference, ICONIP 2014, Kuching, Malaysia, November 3-6, 2014: Proceedings. ed. / Chu Kiong Loo; Keem Siah Yap; Kok Wai Wong; Andrew Teoh; Kaizhu Huang. Vol. Part I Cham: Springer , 2014. p. 279-286 (Lecture Notes in Computer Science; Vol. 8834).

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

TY - CHAP

T1 - The Performance of the Stochastic DNN-kWTA Network

AU - Feng, Ruibin

AU - Leung, Chi-Sing

AU - Ng, Kai-Tat

AU - Sum, John

PY - 2014/11

Y1 - 2014/11

N2 - Recently, the dual neural network (DNN) model has been used to synthesize the k-winners-take-all (kWTA) process. The advantage of this DNN-kWTA model is that its structure is very simple. It contains 2n + 1 connections only. Also, the convergence behavior of the DNN-kWTA model under the noise condition was reported. However, there is no an analytic expression on the equilibrium point. Hence it is difficult to study how the noise condition affects the model performance. This paper studies how the noise condition affects the model performance. Based on the energy function, we propose an efficient method to study the performance of the DNN-kWTA model under the noise condition. Hence we can efficiently study how the noise condition affects the model performance.

AB - Recently, the dual neural network (DNN) model has been used to synthesize the k-winners-take-all (kWTA) process. The advantage of this DNN-kWTA model is that its structure is very simple. It contains 2n + 1 connections only. Also, the convergence behavior of the DNN-kWTA model under the noise condition was reported. However, there is no an analytic expression on the equilibrium point. Hence it is difficult to study how the noise condition affects the model performance. This paper studies how the noise condition affects the model performance. Based on the energy function, we propose an efficient method to study the performance of the DNN-kWTA model under the noise condition. Hence we can efficiently study how the noise condition affects the model performance.

UR - http://www.scopus.com/inward/record.url?scp=84921444724&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-84921444724&origin=recordpage

U2 - 10.1007/978-3-319-12637-1_35

DO - 10.1007/978-3-319-12637-1_35

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

SN - 9783319126364

VL - Part I

T3 - Lecture Notes in Computer Science

SP - 279

EP - 286

BT - Neural Information Processing

A2 - Loo, Chu Kiong

A2 - Yap, Keem Siah

A2 - Wong, Kok Wai

A2 - Teoh, Andrew

A2 - Huang, Kaizhu

PB - Springer

CY - Cham

T2 - 21st International Conference on Neural Information Processing (ICONIP 2014)

Y2 - 3 November 2014 through 6 November 2014

ER -

Feng R, Leung CS, Ng KT, Sum J. The Performance of the Stochastic DNN-kWTA Network. In Loo CK, Yap KS, Wong KW, Teoh A, Huang K, editors, Neural Information Processing: 21st International Conference, ICONIP 2014, Kuching, Malaysia, November 3-6, 2014: Proceedings. Vol. Part I. Cham: Springer . 2014. p. 279-286. (Lecture Notes in Computer Science). doi: 10.1007/978-3-319-12637-1_35

The Performance of the Stochastic DNN-kWTA Network

Abstract

Publication series

Conference

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this