Adaptive Momentum Levenberg-Marquardt RBF for Face Recognition

Sue Inn Ch'ng, Kah Phooi Seng, Li-Minn Ang

Research output: Book chapter/Published conference paperConference paper

1 Citation (Scopus)

Abstract

This paper investigates the application of Levenberg-Marquardt (LM) based radial basis function (RBF) neural networks for face recognition. The contribution of this paper is two-fold. First, we propose the use of Levenberg-Marquardt (LM) and adaptive momentum LM algorithm to update the weights and network parameters (centers and width).The purpose of the proposal of the latter algorithm is to further increase the learning efficiency of the RBF neural network. The second contribution of the paper is the adaptation of the high computational complexity LM-based RBF neural networks to the complex problem of face recognition. To reduce the computations required, dimension reduction was applied prior to the training of the networks. In addition to that, we have also proposed the use of prior knowledge to guess the initial values of the weights during initialization as oppose to random weights. The proposed methods were tested on the Yale database and were found to yield positive results that can further improve the learning efficiency of the networks for the application of face recognition.
Original languageEnglish
Title of host publicationProceedings of the 2012 IEEE International Conference on Circuits and Systems (ICCAS)
Place of PublicationUSA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages126-131
Number of pages6
DOIs
Publication statusPublished - 2012
Event2012 IEEE International Conference on Circuits and Systems: ICCAS - Kuala Lumpur, Malaysia, Kuala Lumpur, Malaysia
Duration: 03 Oct 201204 Oct 2012

Conference

Conference2012 IEEE International Conference on Circuits and Systems
CountryMalaysia
CityKuala Lumpur
Period03/10/1204/10/12

Cite this

Ch'ng, S. I., Seng, K. P., & Ang, L-M. (2012). Adaptive Momentum Levenberg-Marquardt RBF for Face Recognition. In Proceedings of the 2012 IEEE International Conference on Circuits and Systems (ICCAS) (pp. 126-131). USA: IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ICCircuitsAndSystems.2012.6408325
Ch'ng, Sue Inn ; Seng, Kah Phooi ; Ang, Li-Minn. / Adaptive Momentum Levenberg-Marquardt RBF for Face Recognition. Proceedings of the 2012 IEEE International Conference on Circuits and Systems (ICCAS). USA : IEEE, Institute of Electrical and Electronics Engineers, 2012. pp. 126-131
@inproceedings{964b44553db14a05ada1924b7a13ec3a,
title = "Adaptive Momentum Levenberg-Marquardt RBF for Face Recognition",
abstract = "This paper investigates the application of Levenberg-Marquardt (LM) based radial basis function (RBF) neural networks for face recognition. The contribution of this paper is two-fold. First, we propose the use of Levenberg-Marquardt (LM) and adaptive momentum LM algorithm to update the weights and network parameters (centers and width).The purpose of the proposal of the latter algorithm is to further increase the learning efficiency of the RBF neural network. The second contribution of the paper is the adaptation of the high computational complexity LM-based RBF neural networks to the complex problem of face recognition. To reduce the computations required, dimension reduction was applied prior to the training of the networks. In addition to that, we have also proposed the use of prior knowledge to guess the initial values of the weights during initialization as oppose to random weights. The proposed methods were tested on the Yale database and were found to yield positive results that can further improve the learning efficiency of the networks for the application of face recognition.",
keywords = "adaptive momentum, improved Levenberg-Marquardt algorithm, RBF neural networks, face recognition",
author = "Ch'ng, {Sue Inn} and Seng, {Kah Phooi} and Li-Minn Ang",
year = "2012",
doi = "10.1109/ICCircuitsAndSystems.2012.6408325",
language = "English",
pages = "126--131",
booktitle = "Proceedings of the 2012 IEEE International Conference on Circuits and Systems (ICCAS)",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
address = "United States",

}

Ch'ng, SI, Seng, KP & Ang, L-M 2012, Adaptive Momentum Levenberg-Marquardt RBF for Face Recognition. in Proceedings of the 2012 IEEE International Conference on Circuits and Systems (ICCAS). IEEE, Institute of Electrical and Electronics Engineers, USA, pp. 126-131, 2012 IEEE International Conference on Circuits and Systems, Kuala Lumpur, Malaysia, 03/10/12. https://doi.org/10.1109/ICCircuitsAndSystems.2012.6408325

Adaptive Momentum Levenberg-Marquardt RBF for Face Recognition. / Ch'ng, Sue Inn; Seng, Kah Phooi; Ang, Li-Minn.

Proceedings of the 2012 IEEE International Conference on Circuits and Systems (ICCAS). USA : IEEE, Institute of Electrical and Electronics Engineers, 2012. p. 126-131.

Research output: Book chapter/Published conference paperConference paper

TY - GEN

T1 - Adaptive Momentum Levenberg-Marquardt RBF for Face Recognition

AU - Ch'ng, Sue Inn

AU - Seng, Kah Phooi

AU - Ang, Li-Minn

PY - 2012

Y1 - 2012

N2 - This paper investigates the application of Levenberg-Marquardt (LM) based radial basis function (RBF) neural networks for face recognition. The contribution of this paper is two-fold. First, we propose the use of Levenberg-Marquardt (LM) and adaptive momentum LM algorithm to update the weights and network parameters (centers and width).The purpose of the proposal of the latter algorithm is to further increase the learning efficiency of the RBF neural network. The second contribution of the paper is the adaptation of the high computational complexity LM-based RBF neural networks to the complex problem of face recognition. To reduce the computations required, dimension reduction was applied prior to the training of the networks. In addition to that, we have also proposed the use of prior knowledge to guess the initial values of the weights during initialization as oppose to random weights. The proposed methods were tested on the Yale database and were found to yield positive results that can further improve the learning efficiency of the networks for the application of face recognition.

AB - This paper investigates the application of Levenberg-Marquardt (LM) based radial basis function (RBF) neural networks for face recognition. The contribution of this paper is two-fold. First, we propose the use of Levenberg-Marquardt (LM) and adaptive momentum LM algorithm to update the weights and network parameters (centers and width).The purpose of the proposal of the latter algorithm is to further increase the learning efficiency of the RBF neural network. The second contribution of the paper is the adaptation of the high computational complexity LM-based RBF neural networks to the complex problem of face recognition. To reduce the computations required, dimension reduction was applied prior to the training of the networks. In addition to that, we have also proposed the use of prior knowledge to guess the initial values of the weights during initialization as oppose to random weights. The proposed methods were tested on the Yale database and were found to yield positive results that can further improve the learning efficiency of the networks for the application of face recognition.

KW - adaptive momentum

KW - improved Levenberg-Marquardt algorithm

KW - RBF neural networks

KW - face recognition

U2 - 10.1109/ICCircuitsAndSystems.2012.6408325

DO - 10.1109/ICCircuitsAndSystems.2012.6408325

M3 - Conference paper

SP - 126

EP - 131

BT - Proceedings of the 2012 IEEE International Conference on Circuits and Systems (ICCAS)

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - USA

ER -

Ch'ng SI, Seng KP, Ang L-M. Adaptive Momentum Levenberg-Marquardt RBF for Face Recognition. In Proceedings of the 2012 IEEE International Conference on Circuits and Systems (ICCAS). USA: IEEE, Institute of Electrical and Electronics Engineers. 2012. p. 126-131 https://doi.org/10.1109/ICCircuitsAndSystems.2012.6408325