A modified invasive weed optimization algorithm for training of feed-forward neural networks

Ritwik Giri; Aritra Chowdhury; Arnob Ghosh; Swagatam Das; Ajith Abraham; Vaclav Snasel

doi:10.1109/ICSMC.2010.5642265

A modified invasive weed optimization algorithm for training of feed-forward neural networks

Ritwik Giri, Aritra Chowdhury, Arnob Ghosh, Swagatam Das, Ajith Abraham, Vaclav Snasel

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

34 Scopus citations

Abstract

Invasive Weed Optimization Algorithm IWO) is an ecologically inspired metaheuristic that mimics the process of weeds colonization and distribution and is capable of solving multi-dimensional, linear and nonlinear optimization problems with appreciable efficiency. In this article a modified version of IWO has been used for training the feed-forward Artificial Neural Networks (ANNs) by adjusting the weights and biases of the neural network. It has been found that modified IWO performs better than another very competitive real parameter optimizer called Differential Evolution (DE) and a few classical gradient-based optimization algorithms in context to the weight training of feed-forward ANNs in terms of learning rate and solution quality. Moreover, IWO can also be used in validation of reached optima and in the development of regularization terms and non-conventional transfer functions that do not necessarily provide gradient information.

Original language	English (US)
Title of host publication	2010 IEEE International Conference on Systems, Man and Cybernetics, SMC 2010
Pages	3166-3173
Number of pages	8
DOIs	https://doi.org/10.1109/ICSMC.2010.5642265
State	Published - 2010
Externally published	Yes
Event	2010 IEEE International Conference on Systems, Man and Cybernetics, SMC 2010 - Istanbul, Turkey Duration: Oct 10 2010 → Oct 13 2010

Publication series

Name	Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics
ISSN (Print)	1062-922X

Other

Other	2010 IEEE International Conference on Systems, Man and Cybernetics, SMC 2010
Country/Territory	Turkey
City	Istanbul
Period	10/10/10 → 10/13/10

All Science Journal Classification (ASJC) codes

Electrical and Electronic Engineering
Control and Systems Engineering
Human-Computer Interaction

Keywords

Back-propagation
Classification
Differential evolution
Feed-forward neural networks
Invasive weed optimization
Metaheuristics

Access to Document

10.1109/ICSMC.2010.5642265

Cite this

Giri, R., Chowdhury, A., Ghosh, A., Das, S., Abraham, A., & Snasel, V. (2010). A modified invasive weed optimization algorithm for training of feed-forward neural networks. In 2010 IEEE International Conference on Systems, Man and Cybernetics, SMC 2010 (pp. 3166-3173). Article 5642265 (Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics). https://doi.org/10.1109/ICSMC.2010.5642265

@inproceedings{daf4519f834141389eb9af5aa3054591,

title = "A modified invasive weed optimization algorithm for training of feed-forward neural networks",

abstract = "Invasive Weed Optimization Algorithm IWO) is an ecologically inspired metaheuristic that mimics the process of weeds colonization and distribution and is capable of solving multi-dimensional, linear and nonlinear optimization problems with appreciable efficiency. In this article a modified version of IWO has been used for training the feed-forward Artificial Neural Networks (ANNs) by adjusting the weights and biases of the neural network. It has been found that modified IWO performs better than another very competitive real parameter optimizer called Differential Evolution (DE) and a few classical gradient-based optimization algorithms in context to the weight training of feed-forward ANNs in terms of learning rate and solution quality. Moreover, IWO can also be used in validation of reached optima and in the development of regularization terms and non-conventional transfer functions that do not necessarily provide gradient information.",

keywords = "Back-propagation, Classification, Differential evolution, Feed-forward neural networks, Invasive weed optimization, Metaheuristics",

author = "Ritwik Giri and Aritra Chowdhury and Arnob Ghosh and Swagatam Das and Ajith Abraham and Vaclav Snasel",

year = "2010",

doi = "10.1109/ICSMC.2010.5642265",

language = "English (US)",

isbn = "9781424465880",

series = "Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics",

pages = "3166--3173",

booktitle = "2010 IEEE International Conference on Systems, Man and Cybernetics, SMC 2010",

note = "2010 IEEE International Conference on Systems, Man and Cybernetics, SMC 2010 ; Conference date: 10-10-2010 Through 13-10-2010",

}

Giri, R, Chowdhury, A, Ghosh, A, Das, S, Abraham, A & Snasel, V 2010, A modified invasive weed optimization algorithm for training of feed-forward neural networks. in 2010 IEEE International Conference on Systems, Man and Cybernetics, SMC 2010., 5642265, Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics, pp. 3166-3173, 2010 IEEE International Conference on Systems, Man and Cybernetics, SMC 2010, Istanbul, Turkey, 10/10/10. https://doi.org/10.1109/ICSMC.2010.5642265

A modified invasive weed optimization algorithm for training of feed-forward neural networks. / Giri, Ritwik; Chowdhury, Aritra; Ghosh, Arnob et al.
2010 IEEE International Conference on Systems, Man and Cybernetics, SMC 2010. 2010. p. 3166-3173 5642265 (Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - A modified invasive weed optimization algorithm for training of feed-forward neural networks

AU - Giri, Ritwik

AU - Chowdhury, Aritra

AU - Ghosh, Arnob

AU - Das, Swagatam

AU - Abraham, Ajith

AU - Snasel, Vaclav

PY - 2010

Y1 - 2010

N2 - Invasive Weed Optimization Algorithm IWO) is an ecologically inspired metaheuristic that mimics the process of weeds colonization and distribution and is capable of solving multi-dimensional, linear and nonlinear optimization problems with appreciable efficiency. In this article a modified version of IWO has been used for training the feed-forward Artificial Neural Networks (ANNs) by adjusting the weights and biases of the neural network. It has been found that modified IWO performs better than another very competitive real parameter optimizer called Differential Evolution (DE) and a few classical gradient-based optimization algorithms in context to the weight training of feed-forward ANNs in terms of learning rate and solution quality. Moreover, IWO can also be used in validation of reached optima and in the development of regularization terms and non-conventional transfer functions that do not necessarily provide gradient information.

AB - Invasive Weed Optimization Algorithm IWO) is an ecologically inspired metaheuristic that mimics the process of weeds colonization and distribution and is capable of solving multi-dimensional, linear and nonlinear optimization problems with appreciable efficiency. In this article a modified version of IWO has been used for training the feed-forward Artificial Neural Networks (ANNs) by adjusting the weights and biases of the neural network. It has been found that modified IWO performs better than another very competitive real parameter optimizer called Differential Evolution (DE) and a few classical gradient-based optimization algorithms in context to the weight training of feed-forward ANNs in terms of learning rate and solution quality. Moreover, IWO can also be used in validation of reached optima and in the development of regularization terms and non-conventional transfer functions that do not necessarily provide gradient information.

KW - Back-propagation

KW - Classification

KW - Differential evolution

KW - Feed-forward neural networks

KW - Invasive weed optimization

KW - Metaheuristics

UR - http://www.scopus.com/inward/record.url?scp=78751525340&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78751525340&partnerID=8YFLogxK

U2 - 10.1109/ICSMC.2010.5642265

DO - 10.1109/ICSMC.2010.5642265

M3 - Conference contribution

AN - SCOPUS:78751525340

SN - 9781424465880

T3 - Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics

SP - 3166

EP - 3173

BT - 2010 IEEE International Conference on Systems, Man and Cybernetics, SMC 2010

T2 - 2010 IEEE International Conference on Systems, Man and Cybernetics, SMC 2010

Y2 - 10 October 2010 through 13 October 2010

ER -

Giri R, Chowdhury A, Ghosh A, Das S, Abraham A, Snasel V. A modified invasive weed optimization algorithm for training of feed-forward neural networks. In 2010 IEEE International Conference on Systems, Man and Cybernetics, SMC 2010. 2010. p. 3166-3173. 5642265. (Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics). doi: 10.1109/ICSMC.2010.5642265

A modified invasive weed optimization algorithm for training of feed-forward neural networks

Abstract

Publication series

Other

All Science Journal Classification (ASJC) codes

Keywords

Access to Document

Other files and links

Fingerprint

Cite this