File(s) under permanent embargo
An accelerated particle swarm optimization based levenberg marquardt back propagation algorithm
chapter
posted on 2014-01-01, 00:00 authored by N M Nawi, A Khan, M Z Rehman, Maslina Abdul Aziz, T Herawan, Jemal AbawajyJemal AbawajyThe 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.
History
Title of book
Neural information processing : 21st International Conference ICONIP 2014 Kuching, Malaysia, November 3-6, 2014 Proceedings, Part IIVolume
8835Series
Lecture notes in computer scienceChapter number
30Pagination
245 - 253Publisher
Springer VerlagPlace of publication
Heidelberg, GermanyISSN
0302-9743eISSN
1611-3349ISBN-13
9783319126395Language
engPublication classification
B Book chapter; B1 Book chapterCopyright notice
2014, SpringerExtent
71Editor/Contributor(s)
C Loo, K Yap, K Wong, A Teoh, K HuangUsage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC