Cover Image

The impact of VMAX activation function in particle swarm optimization neural network

Back propagation (BP) Network is the most common technique in Artificial Neural Network (ANN) learning. However, major disadvantages of BP are its convergence rate is relatively slow and always being trapped at the local minima. Therefore, latest optimization technique, Particle Swarm Optimization (...

Full description

Saved in:
Bibliographic Details
Main Author: Lee, Yiew Siang
Format: Thesis
Language:English
Published: 2008
Subjects:
QA75 Electronic computers. Computer science
Online Access:http://eprints.utm.my/id/eprint/9456/1/LeeYiewSiangFSKSM2008.pdf
http://eprints.utm.my/id/eprint/9456/
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.utm.9456
record_format eprints
spelling my.utm.94562018-07-19T01:38:53Z http://eprints.utm.my/id/eprint/9456/ The impact of VMAX activation function in particle swarm optimization neural network Lee, Yiew Siang QA75 Electronic computers. Computer science Back propagation (BP) Network is the most common technique in Artificial Neural Network (ANN) learning. However, major disadvantages of BP are its convergence rate is relatively slow and always being trapped at the local minima. Therefore, latest optimization technique, Particle Swarm Optimization (PSO) is chosen and applied in feed forward neural network to enhance the network learning. In conventional PSO, maximum velocity, Vmax serves as a constraint that controls the maximum global exploration ability PSO can have. By setting a too small maximum velocity, maximum global exploration ability is limited and PSO will always favor a local search no matter what the inertia weight is. By setting a large maximum velocity, PSO can have a large range of exploration ability. Therefore, in this study, different activation functions will apply in the PSO Vmax function in order to control global exploration of particles and increase the convergence rate as well as correct classification. The preliminary results show that Vmax hyperbolic tangent function give promising results in term of convergence rate and classification compared to Vmax sigmoid function and standard Vmax function. 2008-06 Thesis NonPeerReviewed application/pdf en http://eprints.utm.my/id/eprint/9456/1/LeeYiewSiangFSKSM2008.pdf Lee, Yiew Siang (2008) The impact of VMAX activation function in particle swarm optimization neural network. Masters thesis, Universiti Teknologi Malaysia, Faculty of Computer Science and Information Systems.
institution Universiti Teknologi Malaysia
building UTM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Malaysia
content_source UTM Institutional Repository
url_provider http://eprints.utm.my/
language English
topic QA75 Electronic computers. Computer science
spellingShingle QA75 Electronic computers. Computer science
Lee, Yiew Siang
The impact of VMAX activation function in particle swarm optimization neural network
description Back propagation (BP) Network is the most common technique in Artificial Neural Network (ANN) learning. However, major disadvantages of BP are its convergence rate is relatively slow and always being trapped at the local minima. Therefore, latest optimization technique, Particle Swarm Optimization (PSO) is chosen and applied in feed forward neural network to enhance the network learning. In conventional PSO, maximum velocity, Vmax serves as a constraint that controls the maximum global exploration ability PSO can have. By setting a too small maximum velocity, maximum global exploration ability is limited and PSO will always favor a local search no matter what the inertia weight is. By setting a large maximum velocity, PSO can have a large range of exploration ability. Therefore, in this study, different activation functions will apply in the PSO Vmax function in order to control global exploration of particles and increase the convergence rate as well as correct classification. The preliminary results show that Vmax hyperbolic tangent function give promising results in term of convergence rate and classification compared to Vmax sigmoid function and standard Vmax function.
format Thesis
author Lee, Yiew Siang
author_facet Lee, Yiew Siang
author_sort Lee, Yiew Siang
title The impact of VMAX activation function in particle swarm optimization neural network
title_short The impact of VMAX activation function in particle swarm optimization neural network
title_full The impact of VMAX activation function in particle swarm optimization neural network
title_fullStr The impact of VMAX activation function in particle swarm optimization neural network
title_full_unstemmed The impact of VMAX activation function in particle swarm optimization neural network
title_sort impact of vmax activation function in particle swarm optimization neural network
publishDate 2008
url http://eprints.utm.my/id/eprint/9456/1/LeeYiewSiangFSKSM2008.pdf
http://eprints.utm.my/id/eprint/9456/
_version_ 1643645160071888896
score 13.211869

Similar Items