Review of deep learning: concepts, CNN architectures, challenges, applications, future directions
Abstract In the last few years, the deep learning (DL) computing paradigm has been deemed the Gold Standard in the machine learning (ML) community. Moreover, it has gradually become the most widely used computational approach in the field of ML, thus achieving outstanding results on several complex...
Main Authors: | , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
SpringerOpen
2021-03-01
|
Series: | Journal of Big Data |
Subjects: | |
Online Access: | https://doi.org/10.1186/s40537-021-00444-8 |
id |
doaj-bdd5bd1947654336a8e41fd116cd6481 |
---|---|
record_format |
Article |
spelling |
doaj-bdd5bd1947654336a8e41fd116cd64812021-04-04T11:44:53ZengSpringerOpenJournal of Big Data2196-11152021-03-018117410.1186/s40537-021-00444-8Review of deep learning: concepts, CNN architectures, challenges, applications, future directionsLaith Alzubaidi0Jinglan Zhang1Amjad J. Humaidi2Ayad Al-Dujaili3Ye Duan4Omran Al-Shamma5J. Santamaría6Mohammed A. Fadhel7Muthana Al-Amidie8Laith Farhan9School of Computer Science, Queensland University of TechnologySchool of Computer Science, Queensland University of TechnologyControl and Systems Engineering Department, University of TechnologyElectrical Engineering Technical College, Middle Technical UniversityFaculty of Electrical Engineering & Computer Science, University of MissouriAlNidhal Campus, University of Information Technology & CommunicationsDepartment of Computer Science, University of JaénCollege of Computer Science and Information Technology, University of SumerFaculty of Electrical Engineering & Computer Science, University of MissouriSchool of Engineering, Manchester Metropolitan UniversityAbstract In the last few years, the deep learning (DL) computing paradigm has been deemed the Gold Standard in the machine learning (ML) community. Moreover, it has gradually become the most widely used computational approach in the field of ML, thus achieving outstanding results on several complex cognitive tasks, matching or even beating those provided by human performance. One of the benefits of DL is the ability to learn massive amounts of data. The DL field has grown fast in the last few years and it has been extensively used to successfully address a wide range of traditional applications. More importantly, DL has outperformed well-known ML techniques in many domains, e.g., cybersecurity, natural language processing, bioinformatics, robotics and control, and medical information processing, among many others. Despite it has been contributed several works reviewing the State-of-the-Art on DL, all of them only tackled one aspect of the DL, which leads to an overall lack of knowledge about it. Therefore, in this contribution, we propose using a more holistic approach in order to provide a more suitable starting point from which to develop a full understanding of DL. Specifically, this review attempts to provide a more comprehensive survey of the most important aspects of DL and including those enhancements recently added to the field. In particular, this paper outlines the importance of DL, presents the types of DL techniques and networks. It then presents convolutional neural networks (CNNs) which the most utilized DL network type and describes the development of CNNs architectures together with their main features, e.g., starting with the AlexNet network and closing with the High-Resolution network (HR.Net). Finally, we further present the challenges and suggested solutions to help researchers understand the existing research gaps. It is followed by a list of the major DL applications. Computational tools including FPGA, GPU, and CPU are summarized along with a description of their influence on DL. The paper ends with the evolution matrix, benchmark datasets, and summary and conclusion.https://doi.org/10.1186/s40537-021-00444-8Deep learningMachine learningConvolution neural network (CNN)Deep neural network architecturesDeep learning applicationsImage classification |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Laith Alzubaidi Jinglan Zhang Amjad J. Humaidi Ayad Al-Dujaili Ye Duan Omran Al-Shamma J. Santamaría Mohammed A. Fadhel Muthana Al-Amidie Laith Farhan |
spellingShingle |
Laith Alzubaidi Jinglan Zhang Amjad J. Humaidi Ayad Al-Dujaili Ye Duan Omran Al-Shamma J. Santamaría Mohammed A. Fadhel Muthana Al-Amidie Laith Farhan Review of deep learning: concepts, CNN architectures, challenges, applications, future directions Journal of Big Data Deep learning Machine learning Convolution neural network (CNN) Deep neural network architectures Deep learning applications Image classification |
author_facet |
Laith Alzubaidi Jinglan Zhang Amjad J. Humaidi Ayad Al-Dujaili Ye Duan Omran Al-Shamma J. Santamaría Mohammed A. Fadhel Muthana Al-Amidie Laith Farhan |
author_sort |
Laith Alzubaidi |
title |
Review of deep learning: concepts, CNN architectures, challenges, applications, future directions |
title_short |
Review of deep learning: concepts, CNN architectures, challenges, applications, future directions |
title_full |
Review of deep learning: concepts, CNN architectures, challenges, applications, future directions |
title_fullStr |
Review of deep learning: concepts, CNN architectures, challenges, applications, future directions |
title_full_unstemmed |
Review of deep learning: concepts, CNN architectures, challenges, applications, future directions |
title_sort |
review of deep learning: concepts, cnn architectures, challenges, applications, future directions |
publisher |
SpringerOpen |
series |
Journal of Big Data |
issn |
2196-1115 |
publishDate |
2021-03-01 |
description |
Abstract In the last few years, the deep learning (DL) computing paradigm has been deemed the Gold Standard in the machine learning (ML) community. Moreover, it has gradually become the most widely used computational approach in the field of ML, thus achieving outstanding results on several complex cognitive tasks, matching or even beating those provided by human performance. One of the benefits of DL is the ability to learn massive amounts of data. The DL field has grown fast in the last few years and it has been extensively used to successfully address a wide range of traditional applications. More importantly, DL has outperformed well-known ML techniques in many domains, e.g., cybersecurity, natural language processing, bioinformatics, robotics and control, and medical information processing, among many others. Despite it has been contributed several works reviewing the State-of-the-Art on DL, all of them only tackled one aspect of the DL, which leads to an overall lack of knowledge about it. Therefore, in this contribution, we propose using a more holistic approach in order to provide a more suitable starting point from which to develop a full understanding of DL. Specifically, this review attempts to provide a more comprehensive survey of the most important aspects of DL and including those enhancements recently added to the field. In particular, this paper outlines the importance of DL, presents the types of DL techniques and networks. It then presents convolutional neural networks (CNNs) which the most utilized DL network type and describes the development of CNNs architectures together with their main features, e.g., starting with the AlexNet network and closing with the High-Resolution network (HR.Net). Finally, we further present the challenges and suggested solutions to help researchers understand the existing research gaps. It is followed by a list of the major DL applications. Computational tools including FPGA, GPU, and CPU are summarized along with a description of their influence on DL. The paper ends with the evolution matrix, benchmark datasets, and summary and conclusion. |
topic |
Deep learning Machine learning Convolution neural network (CNN) Deep neural network architectures Deep learning applications Image classification |
url |
https://doi.org/10.1186/s40537-021-00444-8 |
work_keys_str_mv |
AT laithalzubaidi reviewofdeeplearningconceptscnnarchitectureschallengesapplicationsfuturedirections AT jinglanzhang reviewofdeeplearningconceptscnnarchitectureschallengesapplicationsfuturedirections AT amjadjhumaidi reviewofdeeplearningconceptscnnarchitectureschallengesapplicationsfuturedirections AT ayadaldujaili reviewofdeeplearningconceptscnnarchitectureschallengesapplicationsfuturedirections AT yeduan reviewofdeeplearningconceptscnnarchitectureschallengesapplicationsfuturedirections AT omranalshamma reviewofdeeplearningconceptscnnarchitectureschallengesapplicationsfuturedirections AT jsantamaria reviewofdeeplearningconceptscnnarchitectureschallengesapplicationsfuturedirections AT mohammedafadhel reviewofdeeplearningconceptscnnarchitectureschallengesapplicationsfuturedirections AT muthanaalamidie reviewofdeeplearningconceptscnnarchitectureschallengesapplicationsfuturedirections AT laithfarhan reviewofdeeplearningconceptscnnarchitectureschallengesapplicationsfuturedirections |
_version_ |
1721542417769824256 |