The DOI matches its Crossref record; 85 of the 88 references it cites were found in a registry or an index.
Review of Deep Learning Algorithms and Architectures
Open accessAbstract
Deep learning (DL) is playing an increasingly important role in our lives. It has already made a huge impact in areas, such as cancer diagnosis, precision medicine, self-driving cars, predictive forecasting, and speech recognition. The painstakingly handcrafted feature extractors used in traditional learning, classification, and pattern recognition systems are not scalable for large-sized data sets. In many cases, depending on the problem complexity, DL can also overcome the limitations of earlier shallow networks that prevented efficient training and abstractions of hierarchical representations of multi-dimensional training data. Deep neural network (DNN) uses multiple (deep) layers of units with highly optimized algorithms and architectures. This paper reviews several optimization methods to improve the accuracy of the training and to reduce training time. We delve into the math behind training algorithms used in recent deep networks. We describe current shortcomings, enhancements, and implementations. The review also covers different types of deep architectures, such as deep convolution networks, deep residual networks, recurrent neural networks, reinforcement learning, variational autoencoders, and others.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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?
In the citing paper
“As consistent with the findings for the second and third periods, ANN, Deep Neural Network (DNN), SVM, GA, LR, and DT are among the prominent AI techniques that gained strong traction in recent years (Şerban and Lytras 2020; Shrestha and Mahmood 2019), so are ML, DL, and cognitive AI models in relation to the planning and development of smart cities (Kamrowska-Załuska 2021; Şerban and Lytras 2020”
From Environmentally sustainable smart cities and their converging AI, IoT, and big data technologies and solutions: an integrated approach to an extensive literature review (2023) · cites this paper as Shrestha and Mahmood 2019
In the citing paper
“Deep learning is gaining traction as a type of ANN with more layers of units (Shrestha and Mahmood, 2019).”
From Artificial intelligence for sustainability: Challenges, opportunities, and a research agenda (2020) · cites this paper as Shrestha and Mahmood, 2019
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 5×
“tion with a 152-layer DNN on the ImageNet dataset [62].”
BackgroundMethodInfluentialHochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 2×
“The input, forget and output gates dictates new data going into the cell, what remains in the cell and the cell values used in the calculation of the output of the LSTM block respectively [41], [43].”
MethodAdam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 4×
“Multilayer network training cost on MNIST dataset using different adaptive learning algorithms [58].”
BackgroundMethodInfluentialLeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805 · cited 2×
“7-layer architecture of CNN for character recognition [28].”
BackgroundMethodAdaptation in Natural and Artificial Systems
Holland, J. H. (1992) · The MIT Press eBooks · doi:10.7551/mitpress/1090.001.0001 · Cited by 47,340
(2014) · Cited by 33,419
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S., & Szegedy, C. (2015) · arXiv · doi:10.48550/arxiv.1502.03167 · Cited by 27,818 · cited 2×
“[59] S. Ioffe and C. Szegedy, ‘‘Batch normalization: Accelerating deep network training by reducing internal covariate shift,’’ CoRR, Feb. 2015.”
BackgroundLearning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation
Cho, K., van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1179 · Cited by 25,545 · cited 1×
“GRUs are smaller in size than LSTM as they don’t include the output gate, and can perform better than LSTM on only some simpler datasets [44], [45].”
BackgroundReducing the dimensionality of data with neural networks
Hinton, G. E., & Salakhutdinov, R. R. (2006) · Science · doi:10.1126/science.1127647 · Cited by 20,928
Flagged first, then by citations
3 of the 88 references couldn’t be matched to a known paper.
Research works printed but not linked: 10
- vapnik, 2015, Learning using privileged information: Similarity control and knowledge transfer, J Mach Learn Res, 16, 2023
- ng, 2018, Autoencoders
- 2018, Amazon EC2 P2 & P3 Instances Amazon EC2 Instance Types
- simpson, 2015, Uniform learning in a deep neural network via ‘oddball’ stochastic gradient descent, CoRR
- minsky, 1969, Perceptrons An Introduction to Computational Geometry Expanded Edition, 258
- 2019, Top Deep Learning Github Repositories
- sastry, 2005, Genetic Algorithms
- 10.1017/CBO9780511543241 · DOI
- wu, 2016, Google’s neural machine translation system: Bridging the gap between human and machine translation, CoRR
- metz, 2019, Turing Award Won by 3 Pioneers in Artificial Intelligence, 3b
Cited by
Sorted by citations
Items 1,001–1,001 of 1,001
Source Code Plagiarism Detection Using Siamese BLSTM Network and Embedding Models
Manahi, M., Sulaiman, S., & Bakar, N. S. A. A. (2022) · Lecture Notes in Electrical Engineering · doi:10.1007/978-981-16-8515-6_31 · Cited by 3
Metadata
- Authors
- Shrestha, A., & Mahmood, A.
- Affiliations
- University of Bridgeport (US)
- Venue
- IEEE Access
- Published
- 2019
- Volume
- 7
- Pages
- 53040-53065
- ISSN
- 2169-3536 (ISSN-L)
- OpenAlex
- W2942231644
- Cited by
- 1,883
- References
- 88
- Citations by year
- 2026: 116 · 2025: 317 · 2024: 360 · 2023: 375 · 2022: 297 · 2021: 259 · 2020: 139 · 2019: 20
- FWCI
- 81.55
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- IEEE Access (publishedVersion)
- University of Bridgeport ScholarWorks (University of Bridgeport) (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Stochastic Gradient Optimization Techniques
- Keywords
- deep learning, deep learning architectures, deep convolutional neural networks, ResNet, recurrent neural networks, reinforcement learning, variational autoencoder, feature extraction, hierarchical representation, training time reduction
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.
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
