A Modified AUC for Training Convolutional Neural Networks: Taking Confidence Into Account

Receiver operating characteristic (ROC) curve is an informative tool in binary classification and Area Under ROC Curve (AUC) is a popular metric for reporting performance of binary classifiers. In this paper, first we present a comprehensive review of ROC curve and AUC metric. Next, we propose a mod...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Khashayar Namdar, Masoom A. Haider, Farzad Khalvati
Formato:	article
Lenguaje:	EN
Publicado:	Frontiers Media S.A. 2021
Materias:	AUC ROC CNN binary classification loss function Electronic computers. Computer science QA75.5-76.95
Acceso en línea:	https://doaj.org/article/cdc4554b35574a33b03b9561a0a465be
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:cdc4554b35574a33b03b9561a0a465be
record_format	dspace
spelling	oai:doaj.org-article:cdc4554b35574a33b03b9561a0a465be2021-12-01T19:44:24ZA Modified AUC for Training Convolutional Neural Networks: Taking Confidence Into Account2624-821210.3389/frai.2021.582928https://doaj.org/article/cdc4554b35574a33b03b9561a0a465be2021-11-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/frai.2021.582928/fullhttps://doaj.org/toc/2624-8212Receiver operating characteristic (ROC) curve is an informative tool in binary classification and Area Under ROC Curve (AUC) is a popular metric for reporting performance of binary classifiers. In this paper, first we present a comprehensive review of ROC curve and AUC metric. Next, we propose a modified version of AUC that takes confidence of the model into account and at the same time, incorporates AUC into Binary Cross Entropy (BCE) loss used for training a Convolutional neural Network for classification tasks. We demonstrate this on three datasets: MNIST, prostate MRI, and brain MRI. Furthermore, we have published GenuineAI, a new python library, which provides the functions for conventional AUC and the proposed modified AUC along with metrics including sensitivity, specificity, recall, precision, and F1 for each point of the ROC curve.Khashayar NamdarKhashayar NamdarMasoom A. HaiderMasoom A. HaiderFarzad KhalvatiFarzad KhalvatiFrontiers Media S.A.articleAUCROCCNNbinary classificationloss functionElectronic computers. Computer scienceQA75.5-76.95ENFrontiers in Artificial Intelligence, Vol 4 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	AUC ROC CNN binary classification loss function Electronic computers. Computer science QA75.5-76.95
spellingShingle	AUC ROC CNN binary classification loss function Electronic computers. Computer science QA75.5-76.95 Khashayar Namdar Khashayar Namdar Masoom A. Haider Masoom A. Haider Farzad Khalvati Farzad Khalvati A Modified AUC for Training Convolutional Neural Networks: Taking Confidence Into Account
description	Receiver operating characteristic (ROC) curve is an informative tool in binary classification and Area Under ROC Curve (AUC) is a popular metric for reporting performance of binary classifiers. In this paper, first we present a comprehensive review of ROC curve and AUC metric. Next, we propose a modified version of AUC that takes confidence of the model into account and at the same time, incorporates AUC into Binary Cross Entropy (BCE) loss used for training a Convolutional neural Network for classification tasks. We demonstrate this on three datasets: MNIST, prostate MRI, and brain MRI. Furthermore, we have published GenuineAI, a new python library, which provides the functions for conventional AUC and the proposed modified AUC along with metrics including sensitivity, specificity, recall, precision, and F1 for each point of the ROC curve.
format	article
author	Khashayar Namdar Khashayar Namdar Masoom A. Haider Masoom A. Haider Farzad Khalvati Farzad Khalvati
author_facet	Khashayar Namdar Khashayar Namdar Masoom A. Haider Masoom A. Haider Farzad Khalvati Farzad Khalvati
author_sort	Khashayar Namdar
title	A Modified AUC for Training Convolutional Neural Networks: Taking Confidence Into Account
title_short	A Modified AUC for Training Convolutional Neural Networks: Taking Confidence Into Account
title_full	A Modified AUC for Training Convolutional Neural Networks: Taking Confidence Into Account
title_fullStr	A Modified AUC for Training Convolutional Neural Networks: Taking Confidence Into Account
title_full_unstemmed	A Modified AUC for Training Convolutional Neural Networks: Taking Confidence Into Account
title_sort	modified auc for training convolutional neural networks: taking confidence into account
publisher	Frontiers Media S.A.
publishDate	2021
url	https://doaj.org/article/cdc4554b35574a33b03b9561a0a465be
work_keys_str_mv	AT khashayarnamdar amodifiedaucfortrainingconvolutionalneuralnetworkstakingconfidenceintoaccount AT khashayarnamdar amodifiedaucfortrainingconvolutionalneuralnetworkstakingconfidenceintoaccount AT masoomahaider amodifiedaucfortrainingconvolutionalneuralnetworkstakingconfidenceintoaccount AT masoomahaider amodifiedaucfortrainingconvolutionalneuralnetworkstakingconfidenceintoaccount AT farzadkhalvati amodifiedaucfortrainingconvolutionalneuralnetworkstakingconfidenceintoaccount AT farzadkhalvati amodifiedaucfortrainingconvolutionalneuralnetworkstakingconfidenceintoaccount AT khashayarnamdar modifiedaucfortrainingconvolutionalneuralnetworkstakingconfidenceintoaccount AT khashayarnamdar modifiedaucfortrainingconvolutionalneuralnetworkstakingconfidenceintoaccount AT masoomahaider modifiedaucfortrainingconvolutionalneuralnetworkstakingconfidenceintoaccount AT masoomahaider modifiedaucfortrainingconvolutionalneuralnetworkstakingconfidenceintoaccount AT farzadkhalvati modifiedaucfortrainingconvolutionalneuralnetworkstakingconfidenceintoaccount AT farzadkhalvati modifiedaucfortrainingconvolutionalneuralnetworkstakingconfidenceintoaccount
_version_	1718404656055451648

A Modified AUC for Training Convolutional Neural Networks: Taking Confidence Into Account

Ejemplares similares