Deep learning encodes robust discriminative neuroimaging representations to outperform standard machine learning

Recent critical commentaries unfavorably compare deep learning (DL) with standard machine learning (SML) for brain imaging data analysis. Here, the authors show that if trained following prevalent DL practices, DL methods substantially improve compared to SML methods by encoding robust discriminativ...

Full description

Saved in:
Bibliographic Details
Main Authors: Anees Abrol, Zening Fu, Mustafa Salman, Rogers Silva, Yuhui Du, Sergey Plis, Vince Calhoun
Format: article
Language:EN
Published: Nature Portfolio 2021
Subjects:
Q
Online Access:https://doaj.org/article/74864ec0c1ad472e9740114321893ecf
Tags: Add Tag
No Tags, Be the first to tag this record!
id oai:doaj.org-article:74864ec0c1ad472e9740114321893ecf
record_format dspace
spelling oai:doaj.org-article:74864ec0c1ad472e9740114321893ecf2021-12-02T14:11:45ZDeep learning encodes robust discriminative neuroimaging representations to outperform standard machine learning10.1038/s41467-020-20655-62041-1723https://doaj.org/article/74864ec0c1ad472e9740114321893ecf2021-01-01T00:00:00Zhttps://doi.org/10.1038/s41467-020-20655-6https://doaj.org/toc/2041-1723Recent critical commentaries unfavorably compare deep learning (DL) with standard machine learning (SML) for brain imaging data analysis. Here, the authors show that if trained following prevalent DL practices, DL methods substantially improve compared to SML methods by encoding robust discriminative brain representations.Anees AbrolZening FuMustafa SalmanRogers SilvaYuhui DuSergey PlisVince CalhounNature PortfolioarticleScienceQENNature Communications, Vol 12, Iss 1, Pp 1-17 (2021)
institution DOAJ
collection DOAJ
language EN
topic Science
Q
spellingShingle Science
Q
Anees Abrol
Zening Fu
Mustafa Salman
Rogers Silva
Yuhui Du
Sergey Plis
Vince Calhoun
Deep learning encodes robust discriminative neuroimaging representations to outperform standard machine learning
description Recent critical commentaries unfavorably compare deep learning (DL) with standard machine learning (SML) for brain imaging data analysis. Here, the authors show that if trained following prevalent DL practices, DL methods substantially improve compared to SML methods by encoding robust discriminative brain representations.
format article
author Anees Abrol
Zening Fu
Mustafa Salman
Rogers Silva
Yuhui Du
Sergey Plis
Vince Calhoun
author_facet Anees Abrol
Zening Fu
Mustafa Salman
Rogers Silva
Yuhui Du
Sergey Plis
Vince Calhoun
author_sort Anees Abrol
title Deep learning encodes robust discriminative neuroimaging representations to outperform standard machine learning
title_short Deep learning encodes robust discriminative neuroimaging representations to outperform standard machine learning
title_full Deep learning encodes robust discriminative neuroimaging representations to outperform standard machine learning
title_fullStr Deep learning encodes robust discriminative neuroimaging representations to outperform standard machine learning
title_full_unstemmed Deep learning encodes robust discriminative neuroimaging representations to outperform standard machine learning
title_sort deep learning encodes robust discriminative neuroimaging representations to outperform standard machine learning
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/74864ec0c1ad472e9740114321893ecf
work_keys_str_mv AT aneesabrol deeplearningencodesrobustdiscriminativeneuroimagingrepresentationstooutperformstandardmachinelearning
AT zeningfu deeplearningencodesrobustdiscriminativeneuroimagingrepresentationstooutperformstandardmachinelearning
AT mustafasalman deeplearningencodesrobustdiscriminativeneuroimagingrepresentationstooutperformstandardmachinelearning
AT rogerssilva deeplearningencodesrobustdiscriminativeneuroimagingrepresentationstooutperformstandardmachinelearning
AT yuhuidu deeplearningencodesrobustdiscriminativeneuroimagingrepresentationstooutperformstandardmachinelearning
AT sergeyplis deeplearningencodesrobustdiscriminativeneuroimagingrepresentationstooutperformstandardmachinelearning
AT vincecalhoun deeplearningencodesrobustdiscriminativeneuroimagingrepresentationstooutperformstandardmachinelearning
_version_ 1718391851219681280