Optimisation of neural network with simultaneous feature selection and network prunning using evolutionary algorithm
Most advances on the Evolutionary Algorithm optimisation of Neural Network are on recurrent neural network using the NEAT optimisation method. For feed forward network, most of the optimisation are merely on the Weights and the bias selection which is generally known as conventional Neuroevolution....
Saved in:
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English English |
Published: |
Penerbit UTeM
2015
|
Subjects: | |
Online Access: | https://eprints.ums.edu.my/id/eprint/34974/1/FULL%20TEXT.pdf https://eprints.ums.edu.my/id/eprint/34974/2/ABSTRACT.pdf https://eprints.ums.edu.my/id/eprint/34974/ https://jtec.utem.edu.my/jtec/article/view/1440/951 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.ums.eprints.34974 |
---|---|
record_format |
eprints |
spelling |
my.ums.eprints.349742022-11-30T00:13:53Z https://eprints.ums.edu.my/id/eprint/34974/ Optimisation of neural network with simultaneous feature selection and network prunning using evolutionary algorithm WK Wong Ali Chekima Wong, Kii Ing Law, Kah Haw Lee, Vincent QA71-90 Instruments and machines Most advances on the Evolutionary Algorithm optimisation of Neural Network are on recurrent neural network using the NEAT optimisation method. For feed forward network, most of the optimisation are merely on the Weights and the bias selection which is generally known as conventional Neuroevolution. In this research work, a simultaneous feature reduction, network pruning and weight/biases selection is presented using fitness function design which penalizes selection of large feature sets. The fitness function also considers feature and the neuron reduction in the hidden layer. The results were demonstrated using two sets of data sets which are the cancer datasets and Thyroid datasets. Results showed backpropagation gradient descent error weights/biased optimisations performed slightly better at classification of the two datasets with lower misclassification rate and error. However, features and hidden neurons were reduced with the simultaneous feature /neurons switching using Genetic Algorithm. The number of features were reduced from 21 to 4 (Thyroid dataset) and 9 to 3 (cancer dataset) with only 1 hidden neuron in the processing layer for both network structures for the respective datasets. This research work will present the chromosome representation and the fitness function design. Penerbit UTeM 2015 Article PeerReviewed text en https://eprints.ums.edu.my/id/eprint/34974/1/FULL%20TEXT.pdf text en https://eprints.ums.edu.my/id/eprint/34974/2/ABSTRACT.pdf WK Wong and Ali Chekima and Wong, Kii Ing and Law, Kah Haw and Lee, Vincent (2015) Optimisation of neural network with simultaneous feature selection and network prunning using evolutionary algorithm. Journal of Telecommunication, Electronic and Computer Engineering (JTEC), 8 (12). pp. 83-86. ISSN 2180-1843 (P-ISSN) , 2289-8131 (E-ISSN) https://jtec.utem.edu.my/jtec/article/view/1440/951 |
institution |
Universiti Malaysia Sabah |
building |
UMS Library |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Malaysia Sabah |
content_source |
UMS Institutional Repository |
url_provider |
http://eprints.ums.edu.my/ |
language |
English English |
topic |
QA71-90 Instruments and machines |
spellingShingle |
QA71-90 Instruments and machines WK Wong Ali Chekima Wong, Kii Ing Law, Kah Haw Lee, Vincent Optimisation of neural network with simultaneous feature selection and network prunning using evolutionary algorithm |
description |
Most advances on the Evolutionary Algorithm optimisation of Neural Network are on recurrent neural network using the NEAT optimisation method. For feed forward network, most of the optimisation are merely on the Weights and the bias selection which is generally known as conventional Neuroevolution. In this research work, a simultaneous feature reduction, network pruning and weight/biases selection is presented using fitness function design which penalizes selection of large feature sets. The fitness function also considers feature and the neuron reduction in the hidden layer. The results were demonstrated using two sets of data sets which are the cancer datasets and Thyroid datasets. Results showed backpropagation gradient descent error weights/biased optimisations performed slightly better at classification of the two datasets with lower misclassification rate and error. However, features and hidden neurons were reduced with the simultaneous feature /neurons switching using Genetic Algorithm. The number of features were reduced from 21 to 4 (Thyroid dataset) and 9 to 3 (cancer dataset) with only 1 hidden neuron in the processing layer for both network structures for the respective datasets. This research work will present the chromosome representation and the fitness function design. |
format |
Article |
author |
WK Wong Ali Chekima Wong, Kii Ing Law, Kah Haw Lee, Vincent |
author_facet |
WK Wong Ali Chekima Wong, Kii Ing Law, Kah Haw Lee, Vincent |
author_sort |
WK Wong |
title |
Optimisation of neural network with simultaneous feature selection and network prunning using evolutionary algorithm |
title_short |
Optimisation of neural network with simultaneous feature selection and network prunning using evolutionary algorithm |
title_full |
Optimisation of neural network with simultaneous feature selection and network prunning using evolutionary algorithm |
title_fullStr |
Optimisation of neural network with simultaneous feature selection and network prunning using evolutionary algorithm |
title_full_unstemmed |
Optimisation of neural network with simultaneous feature selection and network prunning using evolutionary algorithm |
title_sort |
optimisation of neural network with simultaneous feature selection and network prunning using evolutionary algorithm |
publisher |
Penerbit UTeM |
publishDate |
2015 |
url |
https://eprints.ums.edu.my/id/eprint/34974/1/FULL%20TEXT.pdf https://eprints.ums.edu.my/id/eprint/34974/2/ABSTRACT.pdf https://eprints.ums.edu.my/id/eprint/34974/ https://jtec.utem.edu.my/jtec/article/view/1440/951 |
_version_ |
1760231367056031744 |
score |
13.18916 |