Lyapunov theory-based multilayered neural network

This brief presents a Lyapunov theory-based weight adaptation scheme for a multilayered neural network (MLNN) mainly used to classify a multiple-input-multiple-output (MIMO) problem. Initially, the MLNN system is linearized using Taylor series expansion. Then, the weight adaptation scheme is designe...

Full description

Bibliographic Details
Main Authors: Lim, Hann, Seng, K., Ang, L., Chin, S.
Format: Journal Article
Published: IEEE Circuits and Systems Society 2009
Online Access:http://hdl.handle.net/20.500.11937/26780
_version_ 1848752083608535040
author Lim, Hann
Seng, K.
Ang, L.
Chin, S.
author_facet Lim, Hann
Seng, K.
Ang, L.
Chin, S.
author_sort Lim, Hann
building Curtin Institutional Repository
collection Online Access
description This brief presents a Lyapunov theory-based weight adaptation scheme for a multilayered neural network (MLNN) mainly used to classify a multiple-input-multiple-output (MIMO) problem. Initially, the MLNN system is linearized using Taylor series expansion. Then, the weight adaptation scheme is designed based on the Lyapunov stability theory to iteratively update the weight. In the design, the Lyapunov function has to be well selected to construct an energy space with a single global minimum. Hence, the Lyapunov theory-based MLNN acts as a MIMO classifier for face recognition. Analysis and discussion on Lyapunov properties of the proposed classifier are included. The performance of the proposed technique is tested on the Olivetti Research Laboratory database for face classification, and some comparisons with existing conventional techniques are given. Simulation results have revealed that our proposed system achieved better performance. © 2009 IEEE.
first_indexed 2025-11-14T08:02:59Z
format Journal Article
id curtin-20.500.11937-26780
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T08:02:59Z
publishDate 2009
publisher IEEE Circuits and Systems Society
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-267802017-09-13T15:29:35Z Lyapunov theory-based multilayered neural network Lim, Hann Seng, K. Ang, L. Chin, S. This brief presents a Lyapunov theory-based weight adaptation scheme for a multilayered neural network (MLNN) mainly used to classify a multiple-input-multiple-output (MIMO) problem. Initially, the MLNN system is linearized using Taylor series expansion. Then, the weight adaptation scheme is designed based on the Lyapunov stability theory to iteratively update the weight. In the design, the Lyapunov function has to be well selected to construct an energy space with a single global minimum. Hence, the Lyapunov theory-based MLNN acts as a MIMO classifier for face recognition. Analysis and discussion on Lyapunov properties of the proposed classifier are included. The performance of the proposed technique is tested on the Olivetti Research Laboratory database for face classification, and some comparisons with existing conventional techniques are given. Simulation results have revealed that our proposed system achieved better performance. © 2009 IEEE. 2009 Journal Article http://hdl.handle.net/20.500.11937/26780 10.1109/TCSII.2009.2015400 IEEE Circuits and Systems Society restricted
spellingShingle Lim, Hann
Seng, K.
Ang, L.
Chin, S.
Lyapunov theory-based multilayered neural network
title Lyapunov theory-based multilayered neural network
title_full Lyapunov theory-based multilayered neural network
title_fullStr Lyapunov theory-based multilayered neural network
title_full_unstemmed Lyapunov theory-based multilayered neural network
title_short Lyapunov theory-based multilayered neural network
title_sort lyapunov theory-based multilayered neural network
url http://hdl.handle.net/20.500.11937/26780