You are not logged in.

An accelerated particle swarm optimization based levenberg marquardt back propagation algorithm

Nawi,NM, Khan,A, Rehman,MZ, Aziz,MA, Tutut Herawan and Jemal H. Abawajy 2014, An accelerated particle swarm optimization based levenberg marquardt back propagation algorithmNeural information processing : 21st International Conference ICONIP 2014 Kuching, Malaysia, November 3-6, 2014 Proceedings, Part II, Springer Verlag, Heidelberg, Germany, pp.245-253, doi: 10.1007/978-3-319-12640-1_30.

Attached Files
Name Description MIMEType Size Downloads

Title An accelerated particle swarm optimization based levenberg marquardt back propagation algorithm
Author(s) Nawi,NM
Khan,A
Rehman,MZ
Aziz,MA
Tutut Herawan
Jemal H. Abawajy
Title of book Neural information processing : 21st International Conference ICONIP 2014 Kuching, Malaysia, November 3-6, 2014 Proceedings, Part II
Publication date 2014
Series Lecture notes in computer science ; v.8835
Chapter number 30
Total chapters 71
Start page 245
End page 253
Total pages 9
Publisher Springer Verlag
Place of Publication Heidelberg, Germany
Keyword(s) Artificial neural networks
Levenberg marquardt back propagation
Meta-heuristic optimization
Nature inspired algorithms
Particle swarm optimization
Summary The Levenberg Marquardt (LM) algorithm is one of the most effective algorithms in speeding up the convergence rate of the Artificial Neural Networks (ANN) with Multilayer Perceptron (MLP) architectures. However, the LM algorithm suffers the problem of local minimum entrapment. Therefore, we introduce several improvements to the Levenberg Marquardt algorithm by training the ANNs with meta-heuristic nature inspired algorithm. This paper proposes a hybrid technique Accelerated Particle Swarm Optimization using Levenberg Marquardt (APSO_LM) to achieve faster convergence rate and to avoid local minima problem. These techniques are chosen since they provide faster training for solving pattern recognition problems using the numerical optimization technique.The performances of the proposed algorithm is evaluated using some bench mark of classification’s datasets. The results are compared with Artificial Bee Colony (ABC) Algorithm using Back Propagation Neural Network (BPNN) algorithm and other hybrid variants. Based on the experimental result, the proposed algorithms APSO_LM successfully demonstrated better performance as compared to other existing algorithms in terms of convergence speed and Mean Squared Error (MSE) by introducing the error and accuracy in network convergence.
ISBN 9783319126395
ISSN 0302-9743
1611-3349
Language eng
DOI 10.1007/978-3-319-12640-1_30
Field of Research 080109 Pattern Recognition and Data Mining
Socio Economic Objective 890101 Fixed Line Data Networks and Services
HERDC Research category B1 Book chapter
ERA Research output type B Book chapter
Copyright notice ©2014, Springer
Persistent URL http://hdl.handle.net/10536/DRO/DU:30069186

Document type: Book Chapter
Collection: School of Information Technology
Connect to link resolver
 
Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 0 times in TR Web of Science
Scopus Citation Count Cited 8 times in Scopus
Google Scholar Search Google Scholar
Access Statistics: 217 Abstract Views, 5 File Downloads  -  Detailed Statistics
Created: Mon, 02 Feb 2015, 09:40:39 EST

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.