The effect of delays on the performance of Layer Recurrent Network

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Layer Recurrent Network (LRN) is a dynamic network that has a feedback loop as well as a delay for each layer of the network except for the last layer. The main objective for this research is to study the effect of delays on the performance of the LRN in identifying a nonlinear model. A numerical experiment of the nonlinear model is set up before a set of input and output data is collected. The collected data is then used to train the LRN. The numbers of delays at the feedback loop is manipulated and the effect of the network performance is observed where it shows that the network has the best performance when the number of delay is set to more than the default/original value (which is one).

Original languageEnglish
Title of host publicationProceedings - CSPA 2010
Subtitle of host publication2010 6th International Colloquium on Signal Processing and Its Applications
DOIs
Publication statusPublished - 17 Sep 2010
Event2010 6th International Colloquium on Signal Processing and Its Applications, CSPA 2010 - Melaka, Malaysia
Duration: 21 May 201023 May 2010

Publication series

NameProceedings - CSPA 2010: 2010 6th International Colloquium on Signal Processing and Its Applications

Other

Other2010 6th International Colloquium on Signal Processing and Its Applications, CSPA 2010
CountryMalaysia
CityMelaka
Period21/05/1023/05/10

Fingerprint

Feedback
Network performance
Experiments

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Signal Processing
  • Control and Systems Engineering

Cite this

Li, T. C., Nordin, F. H., & Yap, K. S. (2010). The effect of delays on the performance of Layer Recurrent Network. In Proceedings - CSPA 2010: 2010 6th International Colloquium on Signal Processing and Its Applications [5545274] (Proceedings - CSPA 2010: 2010 6th International Colloquium on Signal Processing and Its Applications). https://doi.org/10.1109/CSPA.2010.5545274
Li, Tey Ching ; Nordin, Farah Hani ; Yap, Keem Siah. / The effect of delays on the performance of Layer Recurrent Network. Proceedings - CSPA 2010: 2010 6th International Colloquium on Signal Processing and Its Applications. 2010. (Proceedings - CSPA 2010: 2010 6th International Colloquium on Signal Processing and Its Applications).
@inproceedings{22d848fa3bcb4fa29b8b4c2fe5060494,
title = "The effect of delays on the performance of Layer Recurrent Network",
abstract = "Layer Recurrent Network (LRN) is a dynamic network that has a feedback loop as well as a delay for each layer of the network except for the last layer. The main objective for this research is to study the effect of delays on the performance of the LRN in identifying a nonlinear model. A numerical experiment of the nonlinear model is set up before a set of input and output data is collected. The collected data is then used to train the LRN. The numbers of delays at the feedback loop is manipulated and the effect of the network performance is observed where it shows that the network has the best performance when the number of delay is set to more than the default/original value (which is one).",
author = "Li, {Tey Ching} and Nordin, {Farah Hani} and Yap, {Keem Siah}",
year = "2010",
month = "9",
day = "17",
doi = "10.1109/CSPA.2010.5545274",
language = "English",
isbn = "9781424471225",
series = "Proceedings - CSPA 2010: 2010 6th International Colloquium on Signal Processing and Its Applications",
booktitle = "Proceedings - CSPA 2010",

}

Li, TC, Nordin, FH & Yap, KS 2010, The effect of delays on the performance of Layer Recurrent Network. in Proceedings - CSPA 2010: 2010 6th International Colloquium on Signal Processing and Its Applications., 5545274, Proceedings - CSPA 2010: 2010 6th International Colloquium on Signal Processing and Its Applications, 2010 6th International Colloquium on Signal Processing and Its Applications, CSPA 2010, Melaka, Malaysia, 21/05/10. https://doi.org/10.1109/CSPA.2010.5545274

The effect of delays on the performance of Layer Recurrent Network. / Li, Tey Ching; Nordin, Farah Hani; Yap, Keem Siah.

Proceedings - CSPA 2010: 2010 6th International Colloquium on Signal Processing and Its Applications. 2010. 5545274 (Proceedings - CSPA 2010: 2010 6th International Colloquium on Signal Processing and Its Applications).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - The effect of delays on the performance of Layer Recurrent Network

AU - Li, Tey Ching

AU - Nordin, Farah Hani

AU - Yap, Keem Siah

PY - 2010/9/17

Y1 - 2010/9/17

N2 - Layer Recurrent Network (LRN) is a dynamic network that has a feedback loop as well as a delay for each layer of the network except for the last layer. The main objective for this research is to study the effect of delays on the performance of the LRN in identifying a nonlinear model. A numerical experiment of the nonlinear model is set up before a set of input and output data is collected. The collected data is then used to train the LRN. The numbers of delays at the feedback loop is manipulated and the effect of the network performance is observed where it shows that the network has the best performance when the number of delay is set to more than the default/original value (which is one).

AB - Layer Recurrent Network (LRN) is a dynamic network that has a feedback loop as well as a delay for each layer of the network except for the last layer. The main objective for this research is to study the effect of delays on the performance of the LRN in identifying a nonlinear model. A numerical experiment of the nonlinear model is set up before a set of input and output data is collected. The collected data is then used to train the LRN. The numbers of delays at the feedback loop is manipulated and the effect of the network performance is observed where it shows that the network has the best performance when the number of delay is set to more than the default/original value (which is one).

UR - http://www.scopus.com/inward/record.url?scp=77956534328&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77956534328&partnerID=8YFLogxK

U2 - 10.1109/CSPA.2010.5545274

DO - 10.1109/CSPA.2010.5545274

M3 - Conference contribution

AN - SCOPUS:77956534328

SN - 9781424471225

T3 - Proceedings - CSPA 2010: 2010 6th International Colloquium on Signal Processing and Its Applications

BT - Proceedings - CSPA 2010

ER -

Li TC, Nordin FH, Yap KS. The effect of delays on the performance of Layer Recurrent Network. In Proceedings - CSPA 2010: 2010 6th International Colloquium on Signal Processing and Its Applications. 2010. 5545274. (Proceedings - CSPA 2010: 2010 6th International Colloquium on Signal Processing and Its Applications). https://doi.org/10.1109/CSPA.2010.5545274