Pruned committee neural network based on accuracy and diversity trade-off for permeability prediction

Committee Machine (CM) or ensemble introduces a machine learning technique that aggregates some learners or experts to improve generalization performance compared to single member. The constructed CMs are sometimes unnecessarily large and have some drawbacks such as using extra memories, computation...

Full description

Bibliographic Details
Main Authors: Kenari, Seyed Ali Jafari, Mashohor, Syamsiah
Format: Article
Language:English
Published: OMICS International 2014
Online Access:http://psasir.upm.edu.my/id/eprint/35100/
http://psasir.upm.edu.my/id/eprint/35100/1/35100.pdf
_version_ 1848847960068063232
author Kenari, Seyed Ali Jafari
Mashohor, Syamsiah
author_facet Kenari, Seyed Ali Jafari
Mashohor, Syamsiah
author_sort Kenari, Seyed Ali Jafari
building UPM Institutional Repository
collection Online Access
description Committee Machine (CM) or ensemble introduces a machine learning technique that aggregates some learners or experts to improve generalization performance compared to single member. The constructed CMs are sometimes unnecessarily large and have some drawbacks such as using extra memories, computational overhead, and occasional decrease in effectiveness. Pruning some members of this committee while preserving a high diversity among the individual experts is an efficient technique to increase the predictive performance. The diversity between committee members is a very important measurement parameter which is not necessarily independent of their accuracy and essentially there is a tradeoff between them. In this paper, first we constructed a committee neural network with different learning algorithms and then proposed an expert pruning method based on diversity and accuracy tradeoff to improve the committee machine framework. Finally we applied this proposed structure to predict permeability values from well log data with the aid of available core data. The results show that our method gives the lowest error and highest correlation coefficient compared to the best expert and the initial committee machine and also produces significant information on the reliability of the permeability predictions.
first_indexed 2025-11-15T09:26:54Z
format Article
id upm-35100
institution Universiti Putra Malaysia
institution_category Local University
language English
last_indexed 2025-11-15T09:26:54Z
publishDate 2014
publisher OMICS International
recordtype eprints
repository_type Digital Repository
spelling upm-351002016-10-11T02:27:23Z http://psasir.upm.edu.my/id/eprint/35100/ Pruned committee neural network based on accuracy and diversity trade-off for permeability prediction Kenari, Seyed Ali Jafari Mashohor, Syamsiah Committee Machine (CM) or ensemble introduces a machine learning technique that aggregates some learners or experts to improve generalization performance compared to single member. The constructed CMs are sometimes unnecessarily large and have some drawbacks such as using extra memories, computational overhead, and occasional decrease in effectiveness. Pruning some members of this committee while preserving a high diversity among the individual experts is an efficient technique to increase the predictive performance. The diversity between committee members is a very important measurement parameter which is not necessarily independent of their accuracy and essentially there is a tradeoff between them. In this paper, first we constructed a committee neural network with different learning algorithms and then proposed an expert pruning method based on diversity and accuracy tradeoff to improve the committee machine framework. Finally we applied this proposed structure to predict permeability values from well log data with the aid of available core data. The results show that our method gives the lowest error and highest correlation coefficient compared to the best expert and the initial committee machine and also produces significant information on the reliability of the permeability predictions. OMICS International 2014 Article PeerReviewed application/pdf en http://psasir.upm.edu.my/id/eprint/35100/1/35100.pdf Kenari, Seyed Ali Jafari and Mashohor, Syamsiah (2014) Pruned committee neural network based on accuracy and diversity trade-off for permeability prediction. Journal of Geology & Geosciences, 3 (2). art. no. 144. pp. 1-8. ISSN 2329-6755 http://www.omicsgroup.org/journals/pruned-committee-neural-network-based-on-accuracy-and-diversity-trade-off-for-permeability-prediction-2329-6755.1000144.php?aid=24772 10.4172/2329-6755.1000144
spellingShingle Kenari, Seyed Ali Jafari
Mashohor, Syamsiah
Pruned committee neural network based on accuracy and diversity trade-off for permeability prediction
title Pruned committee neural network based on accuracy and diversity trade-off for permeability prediction
title_full Pruned committee neural network based on accuracy and diversity trade-off for permeability prediction
title_fullStr Pruned committee neural network based on accuracy and diversity trade-off for permeability prediction
title_full_unstemmed Pruned committee neural network based on accuracy and diversity trade-off for permeability prediction
title_short Pruned committee neural network based on accuracy and diversity trade-off for permeability prediction
title_sort pruned committee neural network based on accuracy and diversity trade-off for permeability prediction
url http://psasir.upm.edu.my/id/eprint/35100/
http://psasir.upm.edu.my/id/eprint/35100/
http://psasir.upm.edu.my/id/eprint/35100/
http://psasir.upm.edu.my/id/eprint/35100/1/35100.pdf