Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 358 of the 372 references it cites were found in a registry or an index; 137 of the 246 sources its claims cite were checked for support.

Review of deep learning: concepts, CNN architectures, challenges, applications, future directions

Open access

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.

Overview

CoChat Summary

## TL;DR

This paper is a broad review of deep learning that explains core concepts, classifies DL approaches, and surveys CNN architectures from AlexNet to HRNet. It also summarizes major challenges, applications, and computational platforms, with a heavy emphasis on medical imaging and CNN-based solutions.

## Key findings

  • The authors reviewed more than 300 papers on deep learning topics, with 108 papers from 2020, 76 from 2019, and 48 from 2018.
  • They argue that DL can reduce manual feature engineering by learning features automatically and that it has already achieved strong results in tasks such as image classification, detection, segmentation, and registration.
  • The paper highlights that CNNs are the most used DL network type and reviews their architectural evolution from AlexNet (2012) to HRNet (2020).
  • It identifies major DL challenges including lack of training data, imbalanced data, interpretability, uncertainty scaling, catastrophic forgetting, model compression, overfitting, vanishing/exploding gradients, and underspecification.

## Methods

  • This is a survey/review paper, not an experimental study.
  • The authors report reviewing literature from 2010–2020 (mainly 2020 and 2019, with some 2021 papers), drawing from publishers including IEEE, Elsevier, MDPI, Nature, ACM, and Springer, plus some arXiv papers.
  • Their review was organized to cover DL approaches and network types, CNN architectures, challenges and solutions, applications, and computational approaches.

## Limitations

  • The paper itself states that the review is not exhaustive for every topic; for example, in registration it says it is “out of the scope of this work to provide an extensive review of this topic.”
  • The text also makes evident that some sections are descriptive rather than systematic: it summarizes many studies and architectures but does not report a formal meta-analysis or quantitative comparison across all included papers. (This is evident from the text.)
  • Several sections are labeled only as headings or brief placeholders in the provided text, suggesting the supplied version is fragmentary/incomplete in places. (This is evident from the text.)

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.1186/s40537-021-00444-8

Cites

358 of 359 references verified0 citation errors · 1 not checkable

Statistics

Nothing to recompute.

Figures

Fig. 1 Search framework
Fig. 1 Search frameworkCC BY · PubMed Central
Fig. 2 Deep learning family
Fig. 2 Deep learning familyCC BY · PubMed Central
Fig. 3 The difference between deep learning and traditional machine learning
Fig. 3 The difference between deep learning and traditional machine learningCC BY · PubMed Central
Fig. 4 Deep learning performance compared to human
Fig. 4 Deep learning performance compared to humanCC BY · PubMed Central
Fig. 5 An example of RvNN tree
Fig. 5 An example of RvNN treeCC BY · PubMed Central
Fig. 6 Typical unfolded RNN diagram
Fig. 6 Typical unfolded RNN diagramCC BY · PubMed Central
Fig. 7 An example of CNN architecture for image classification
Fig. 7 An example of CNN architecture for image classificationCC BY · PubMed Central
Fig. 8 The primary calculations executed at each step of convolutional layer
Fig. 8 The primary calculations executed at each step of convolutional layerCC BY · PubMed Central
Fig. 9 Three types of pooling operations
Fig. 9 Three types of pooling operationsCC BY · PubMed Central
Fig. 10 Fully connected layer
Fig. 10 Fully connected layerCC BY · PubMed Central
Fig. 11 Over-fitting and under-fitting issues
Fig. 11 Over-fitting and under-fitting issuesCC BY · PubMed Central
Fig. 12 MLP structure
Fig. 12 MLP structureCC BY · PubMed Central
Fig. 13 Neuron activation functions
Fig. 13 Neuron activation functionsCC BY · PubMed Central
Fig. 14 The architecture of LeNet
Fig. 14 The architecture of LeNetCC BY · PubMed Central
Fig. 15 The architecture of AlexNet
Fig. 15 The architecture of AlexNetCC BY · PubMed Central
Fig. 16 The architecture of network-in-network
Fig. 16 The architecture of network-in-networkCC BY · PubMed Central
Fig. 17 The architecture of ZefNet
Fig. 17 The architecture of ZefNetCC BY · PubMed Central
Fig. 18 The architecture of VGG
Fig. 18 The architecture of VGGCC BY · PubMed Central
Fig. 19 The basic structure of Google Block
Fig. 19 The basic structure of Google BlockCC BY · PubMed Central
Fig. 20 The block diagram for ResNet
Fig. 20 The block diagram for ResNetCC BY · PubMed Central
Fig. 21 The basic block diagram for Inception Residual unit
Fig. 21 The basic block diagram for Inception Residual unitCC BY · PubMed Central
Fig. 22 The architecture of DenseNet Network (adopted from [112])
Fig. 22 The architecture of DenseNet Network (adopted from [112])CC BY · PubMed Central
Fig. 23 The basic block diagram for the ResNext building blocks
Fig. 23 The basic block diagram for the ResNext building blocksCC BY · PubMed Central
Fig. 24 The basic block diagram for the Xception block architecture
Fig. 24 The basic block diagram for the Xception block architectureCC BY · PubMed Central
Fig. 25 The complete CapsNet encoding and decoding processes
Fig. 25 The complete CapsNet encoding and decoding processesCC BY · PubMed Central
Fig. 26 The general architecture of HRNet
Fig. 26 The general architecture of HRNetCC BY · PubMed Central
Fig. 27 The performance of DL regarding the amount of data
Fig. 27 The performance of DL regarding the amount of dataCC BY · PubMed Central
Fig. 28 The conceptual diagram of the TL technique
Fig. 28 The conceptual diagram of the TL techniqueCC BY · PubMed Central
Fig. 29 Examples of DL applications
Fig. 29 Examples of DL applicationsCC BY · PubMed Central
Fig. 30 Workflow of deep learning tasks
Fig. 30 Workflow of deep learning tasksCC BY · PubMed Central

Verification

Claims the paper makes

81 Valid · 73 Not valid · 62 Not checked · 158 Own results and interpretations

93 more claims · 31 with their cited sources checked

Create a free account to see all 374 claims and to verify the 5 references still open.

See all claims — free account
  • Probably not a substantial claim. 224
  • It may state two separate claims as one. 109
  • The quote only partly states this claim. 2

Create a free account to see these claims.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

Self-check results appear here once an independent check has confirmed them.

Cited works that were retracted

Works this paper cites that were later retracted, from the retraction notices publishers deposit. Major when the notice came out before this paper was published.

1 of 1

Citations

Cites

1 retracted

Show all 372 references

Research works printed but not linked: 4

  1. Erhan D, Bengio Y, Courville A, Vincent P. Visualizing higher-layer features of a deep network. Univ Montreal. 2009;1341(3):1.
  2. Ribeiro AH, Tiels K, Aguirre LA, Schön T. Beyond exploding and vanishing gradients: analysing RNN training using attractors and smoothness. In: International conference on artificial intelligence and statistics, PMLR; 2020. p. 2370–80.
  3. Zhao H, Han Z, Yang Z, Zhang Q, Yang F, Zhou L, Yang M, Lau FC, Wang Y, Xiong Y, et al. Hived: sharing a {GPU} cluster for deep learning with guarantees. In: 14th {USENIX} symposium on operating systems design and implementation ({OSDI} 20); 2020. p. 515–32.
  4. Rakotomamonyj A. Optimizing area under roc with SVMS. In: Proceedings of the European conference on artificial intelligence workshop on ROC curve and artificial intelligence (ROCAI 2004), 2004. p. 71–80.

Cited by

See all 7,964

Metadata

Authors
Alzubaidi, L., Zhang, J., Humaidi, A. J., Al-Dujaili, A., Duan, Y., Al-Shamma, O., Santamaría, J., Fadhel, M. A., Al-Amidie, M., & Farhan, L.
Affiliations
  • Queensland University of Technology (AU)
  • University of Technology - Iraq (IQ)
  • Middle Technical University (IQ)
  • University of Missouri (US)
  • University of Information Technology and Communications (IQ)
  • Universidad de Jaén (ES)
  • University of Sumer (IQ)
  • Manchester Metropolitan University (GB)
Corresponding author
Alzubaidi, Laith
Venue
Journal of Big Data
Published
2021-03-31
Volume
8
Issue
1
Pages
53-53
ISSN
2196-1115 (ISSN-L)
OpenAlex
W3140854437
Cited by
7,906
References
372
Citations by year
2026: 1140 · 2025: 2146 · 2024: 2166 · 2023: 1583 · 2022: 719 · 2021: 152
FWCI
414.94
Type
journal article
Language
en
Open access
Licence
Locations
  • Journal Of Big Data (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • RUJA. Institutional Repository of Scientific Production of the University of Jaén (University of Jaén) (publishedVersion, cc-by-nc-nd)
  • QUT ePrints (Queensland University of Technology) (submittedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
Queensland University of Technology
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
  • Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
  • Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
Keywords
deep learning, convolutional neural networks, convolutional neural network architecture, AlexNet, HRNet, deep learning applications, FPGA, graphics processing units, CPU, benchmark dataset

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

The claim verdicts this report counts are experimental: their accuracy is not yet measured.

A language model drew the claims from the paper on 2026-09-28, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).

A second model labelled each claim on 2026-09-28 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).

Cited sources are checked with a language model’s help (gpt-6-sol).

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Review of deep learning: concepts, CNN architectures, challenges, applications, future directions. https://app.cochat.ai/papers/10.1186/s40537-021-00444-8
The paper
Alzubaidi, L., Zhang, J., Humaidi, A. J., Al-Dujaili, A., Duan, Y., Al-Shamma, O., Santamaría, J., Fadhel, M. A., Al-Amidie, M., & Farhan, L. (2021). Review of deep learning: concepts, CNN architectures, challenges, applications, future directions. Journal of Big Data. https://doi.org/10.1186/s40537-021-00444-8

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.