Cover Image

Effect of chaos noise on the learning ability of back propagation algorithm in feed forward neural network

Link to publisher's homepage at http://ieeexplore.ieee.org/

Saved in:
Bibliographic Details
Main Authors: Azian Azamimi, Uwate, Yoko, Nishio, Yoshifumi
Format: Working Paper
Language:English
Published: Institute of Electrical and Elctronics Engineering (IEEE) 2010
Subjects:
Chaos noise
Back propagation
Neural networks
Learning algorithm
International Colloquium on Signal Processing & Its Applications (CSPA)
Online Access:http://dspace.unimap.edu.my/xmlui/handle/123456789/9080
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.unimap-9080
record_format dspace
spelling my.unimap-90802010-08-25T02:53:40Z Effect of chaos noise on the learning ability of back propagation algorithm in feed forward neural network Azian Azamimi Uwate, Yoko Nishio, Yoshifumi Chaos noise Back propagation Neural networks Learning algorithm International Colloquium on Signal Processing & Its Applications (CSPA) Link to publisher's homepage at http://ieeexplore.ieee.org/ In the area of artificial neural networks, the Back Propagation (BP) learning algorithm has proved to be efficient in many engineering applications especially in pattern recognition, signal processing and system control. Although the BP learning has been a significant research area of neural network, it has also been known as an algorithm with a poor convergence rate. Many attempts have been made on the learning algorithm to improve the performance on convergence speed and learning efficiency. In this study, we propose a new modified BP learning algorithm by adding chaotic noise into weight update process during error propagation. The chaotic noise is generated using various chaotic maps such as Logistic map, Skew Tent map and Bernoulli Shift map. By computer simulations, we confirm that our proposed algorithm can give a better convergence rate and can find a good solution in early time compared to the conventional BP learning algorithm. Weight update position, noise amplitude and control parameter of chaos can give a big effect on the learning ability of feed forward neural network. 2010-08-25T02:53:40Z 2010-08-25T02:53:40Z 2010-04-21 Working Paper p.1-4 978-1-4244-7121-8 http://ezproxy.unimap.edu.my:2080/search/srchabstract.jsp?tp=&arnumber=5545250&queryText%3DEffect+of+Chaos+Noise%26openedRefinements%3D*%26searchField%3DSearch+All http://hdl.handle.net/123456789/9080 en Proceedings of the 6th International Colloqium on Signal Processing & Its Applications (CSPA) 2010 Institute of Electrical and Elctronics Engineering (IEEE)
institution Universiti Malaysia Perlis
building UniMAP Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Malaysia Perlis
content_source UniMAP Library Digital Repository
url_provider http://dspace.unimap.edu.my/
language English
topic Chaos noise
Back propagation
Neural networks
Learning algorithm
International Colloquium on Signal Processing & Its Applications (CSPA)
spellingShingle Chaos noise
Back propagation
Neural networks
Learning algorithm
International Colloquium on Signal Processing & Its Applications (CSPA)
Azian Azamimi
Uwate, Yoko
Nishio, Yoshifumi
Effect of chaos noise on the learning ability of back propagation algorithm in feed forward neural network
description Link to publisher's homepage at http://ieeexplore.ieee.org/
format Working Paper
author Azian Azamimi
Uwate, Yoko
Nishio, Yoshifumi
author_facet Azian Azamimi
Uwate, Yoko
Nishio, Yoshifumi
author_sort Azian Azamimi
title Effect of chaos noise on the learning ability of back propagation algorithm in feed forward neural network
title_short Effect of chaos noise on the learning ability of back propagation algorithm in feed forward neural network
title_full Effect of chaos noise on the learning ability of back propagation algorithm in feed forward neural network
title_fullStr Effect of chaos noise on the learning ability of back propagation algorithm in feed forward neural network
title_full_unstemmed Effect of chaos noise on the learning ability of back propagation algorithm in feed forward neural network
title_sort effect of chaos noise on the learning ability of back propagation algorithm in feed forward neural network
publisher Institute of Electrical and Elctronics Engineering (IEEE)
publishDate 2010
url http://dspace.unimap.edu.my/xmlui/handle/123456789/9080
_version_ 1643789402775748608
score 13.214268

Similar Items