Deep Convolutional Neural Network Ensembles Using ECOC

Deep neural networks have enhanced the performance of decision making systems in many applications, including image understanding, and further gains can be achieved by constructing ensembles. However, designing an ensemble of deep networks is often not very beneficial since the time needed to train...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Sara Atito Ali Ahmed, Cemre Zor, Muhammad Awais, Berrin Yanikoglu, Josef Kittler
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Deep learning ensemble learning error correcting output coding gradient boosting decision trees multi-task classification Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/d0e8b725deaf445ea43c6b007215d0b0
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:d0e8b725deaf445ea43c6b007215d0b0
record_format	dspace
spelling	oai:doaj.org-article:d0e8b725deaf445ea43c6b007215d0b02021-11-25T00:00:15ZDeep Convolutional Neural Network Ensembles Using ECOC2169-353610.1109/ACCESS.2021.3088717https://doaj.org/article/d0e8b725deaf445ea43c6b007215d0b02021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9452167/https://doaj.org/toc/2169-3536Deep neural networks have enhanced the performance of decision making systems in many applications, including image understanding, and further gains can be achieved by constructing ensembles. However, designing an ensemble of deep networks is often not very beneficial since the time needed to train the networks is generally very high or the performance gain obtained is not very significant. In this paper, we analyse an error correcting output coding (ECOC) framework for constructing ensembles of deep networks and propose different design strategies to address the accuracy-complexity trade-off. We carry out an extensive comparative study between the introduced ECOC designs and the state-of-the-art ensemble techniques such as ensemble averaging and gradient boosting decision trees. Furthermore, we propose a fusion technique, that is shown to achieve the highest classification performance.Sara Atito Ali AhmedCemre ZorMuhammad AwaisBerrin YanikogluJosef KittlerIEEEarticleDeep learningensemble learningerror correcting output codinggradient boosting decision treesmulti-task classificationElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 86083-86095 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Deep learning ensemble learning error correcting output coding gradient boosting decision trees multi-task classification Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Deep learning ensemble learning error correcting output coding gradient boosting decision trees multi-task classification Electrical engineering. Electronics. Nuclear engineering TK1-9971 Sara Atito Ali Ahmed Cemre Zor Muhammad Awais Berrin Yanikoglu Josef Kittler Deep Convolutional Neural Network Ensembles Using ECOC
description	Deep neural networks have enhanced the performance of decision making systems in many applications, including image understanding, and further gains can be achieved by constructing ensembles. However, designing an ensemble of deep networks is often not very beneficial since the time needed to train the networks is generally very high or the performance gain obtained is not very significant. In this paper, we analyse an error correcting output coding (ECOC) framework for constructing ensembles of deep networks and propose different design strategies to address the accuracy-complexity trade-off. We carry out an extensive comparative study between the introduced ECOC designs and the state-of-the-art ensemble techniques such as ensemble averaging and gradient boosting decision trees. Furthermore, we propose a fusion technique, that is shown to achieve the highest classification performance.
format	article
author	Sara Atito Ali Ahmed Cemre Zor Muhammad Awais Berrin Yanikoglu Josef Kittler
author_facet	Sara Atito Ali Ahmed Cemre Zor Muhammad Awais Berrin Yanikoglu Josef Kittler
author_sort	Sara Atito Ali Ahmed
title	Deep Convolutional Neural Network Ensembles Using ECOC
title_short	Deep Convolutional Neural Network Ensembles Using ECOC
title_full	Deep Convolutional Neural Network Ensembles Using ECOC
title_fullStr	Deep Convolutional Neural Network Ensembles Using ECOC
title_full_unstemmed	Deep Convolutional Neural Network Ensembles Using ECOC
title_sort	deep convolutional neural network ensembles using ecoc
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/d0e8b725deaf445ea43c6b007215d0b0
work_keys_str_mv	AT saraatitoaliahmed deepconvolutionalneuralnetworkensemblesusingecoc AT cemrezor deepconvolutionalneuralnetworkensemblesusingecoc AT muhammadawais deepconvolutionalneuralnetworkensemblesusingecoc AT berrinyanikoglu deepconvolutionalneuralnetworkensemblesusingecoc AT josefkittler deepconvolutionalneuralnetworkensemblesusingecoc
_version_	1718414723119054848

Deep Convolutional Neural Network Ensembles Using ECOC

Ejemplares similares