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 901–1,000 of 1,001
Collaborative Filtering Recommendation Systems Based on Deep Learning: An Experimental Study
Pardo, E., Valdiviezo-Díaz, P., Barba-Guamán, L., & Chicaiza, J. A. (2024) · Lecture notes in networks and systems · doi:10.1007/978-3-031-60218-4_6 · Cited by 6
Multiscale dilated convolutional neural network for Atrial Fibrillation detection
Xia, L., He, S., Huang, Y.-F., & Ma, H. (2024) · PLoS ONE · doi:10.1371/journal.pone.0301691 · Cited by 6
Automatic detection of fish scale circuli using deep learning
Hanson, N. N., Ounsley, J., Henry, J., Terzić, K., & Caneco, B. (2024) · Biology Methods and Protocols · doi:10.1093/biomethods/bpae056 · Cited by 6
“Recent advancements in deep learning and specifically CNNs [15–17] have led to the development of numerous tools which are highly proficient at locating objects within images.”
BackgroundArtificial Intelligence Techniques for Dynamic Offloading in Cloud Continuum Environment: A Review
Pezzullo, G., & Martino, B. D. (2024) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-3-031-70011-8_38 · Cited by 6
Chompookham, T., Phiphitphatphaisit, S., Okafor, E., & Surinta, O. (2024) · IEEE Access · doi:10.1109/access.2024.3457753 · Cited by 6
“Deep learning techniques aim to discover the optimal parameters by iteratively training models to minimize a given function to its local minimum [63], [64].”
BackgroundA Data-Driven Online Prediction Model for Battery Charging Efficiency Accounting for Entropic Heat
Ding, X., Zhang, W., Yuan, C., Ge, C., Bao, Y., An, Z., Liu, Q., Wang, Z., Shi, J., & Wang, Z. (2024) · Batteries · doi:10.3390/batteries10100350 · Cited by 6
Constructing a metadata knowledge graph as an atlas for demystifying AI pipeline optimization
Venkataramanan, R., Tripathy, A., Kumar, T., Serebryakov, S., Koomthanam, A. J., Shah, A., Bhattacharya, S., Foltín, M., Faraboschi, P., Roy, K., et al. (2025) · Frontiers in Big Data · doi:10.3389/fdata.2024.1476506 · Cited by 6
Yang, C., Sun, L., Zhang, J., Fan, X., Zhang, D., Ren, T., Liu, M., Zhang, Z., & Ma, W. (2025) · Frontiers in Plant Science · doi:10.3389/fpls.2024.1458962 · Cited by 6
Dautov, K., Tolebi, G., Hashmi, M., Jarndal, A., Almajali, E. R., & Nauryzbayev, G. (2025) · IEEE Access · doi:10.1109/access.2025.3545141 · Cited by 6
“Additionally, the number of layers is denoted as (cid:57) ∈ N , where N ∈ N ( (cid:57) + 1) , N 0 , N (cid:57) , and N ψ , ψ ∈ [ (cid:57) − 1] are the numbers of neurons in the input, output, and ψ th hidden layers, accordingly [33].”
Nira, & Kumar, H. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-12450-w · Cited by 7
“B Kamal Kapoor, Director and Co-Founder, Sharp Sight Eye Hospitals, said that India ’ s adult population has an estimated 73 million cases of diabetes [84, 86].”
BackgroundMUSAK: A Multi-Scale Space Kinematic Method for Drone Detection
Liu, S., Li, G., Zhan, Y., & Gao, P. (2022) · Remote Sensing · doi:10.3390/rs14061434 · Cited by 6
Soft computing and image processing techniques for COVID-19 prediction in lung CT scan images
Appari, N. V. L., & Kanojia, M. G. (2022) · International Journal of Hybrid Intelligent Systems · doi:10.3233/his-220009 · Cited by 6
Behavior of Square Footing Erected on Gypseous Soil Treated by Ceramic Wastes
Ahmed, A. A. H., & Zedan, A. J. (2022) · Tikrit Journal of Engineering Sciences · doi:10.25130/tjes.29.2.3 · Cited by 6
“Mahmood, 2019 [8] presents experimental results to determine the optimum length to diameter ratio of”
BackgroundDeep Learning in Predicting High School Grades: A Quantum Space of Representation
Mendes, R., Cruz‐Jesus, F., Oliveira, T., & Castelli, M. (2022) · Emerging Science Journal · doi:10.28991/esj-2022-sied-012 · Cited by 6
“Page | 171 3-2-5-1- Mini-Batch Gradient Descent with Momentum The batch gradient descent [3] with moment updates the weights and biases wt for a learning rate η and a momentum hyperparameter β are as following:”
BackgroundMethodLi, J., Kwong, P. W.-H., Lua, E. K., Chan, M. Y. L., Choo, A., & Donnelly, C. (2022) · Topics in Stroke Rehabilitation · doi:10.1080/10749357.2022.2127669 · Cited by 6
“It helps to analyze highdimensional, large-sized data sets using multiple layers, high-performance architectures neural networks.(8) Convolutional neural networks (CNN) is a kind of deep learning algorithm.”
BackgroundMachine learning for Arabic phonemes recognition using electrolarynx speech
Ameen, Z. J. M., & Kadhim, A. A. (2022) · International Journal of Power Electronics and Drive Systems/International Journal of Electrical and Computer Engineering · doi:10.11591/ijece.v13i1.pp400-412 · Cited by 6
Fisher, M. T., Jurkenas, D., Jambajantsan, A., Jamsranjav, B., Nasan-Ochir, E.-O., Gelegdorj, E., Chuluunbat, M., Petraglia, M., & Boivin, N. (2022) · F1000Research · doi:10.12688/f1000research.126740.1 · Cited by 7
“…of typically four layers that first sort pixel values (input layer), then filter pixels to identify edges (convolutional layer), then pool values (pooling layer), and finally connect all layers and assign a unique value to each object (fully-connected layer; Shrestha & Mahmood 2019: 53044).”
BackgroundKannan, M., Sundareswaran, K., Nayak, P. S. R., & Simon, S. P. (2022) · Journal of The Institution of Engineers (India) Series B · doi:10.1007/s40031-022-00848-x · Cited by 6
“There are various approaches to the SoC estimate problem [3], [4].”
MethodIndividualized risk assessment of preoperative opioid use by interpretable neural network regression
Sun, Y., Kang, J., Brummett, C. M., & Li, Y. (2023) · The Annals of Applied Statistics · doi:10.1214/22-aoas1634 · Cited by 5
Cyber Threat Intelligence Discovery using Machine Learning from the Dark Web
(2023) · Communications of the IIMA · doi:10.58729/1941-6687.1436 · Cited by 6
“Figure 5 present the deep learning model (Shrestha & Mahmood, 2019; Chen and et al, 2020) where we use two hidden, input and output layers.”
MethodSharon, J. A., Christinal, H. A., Chandy, D. A., & Bajaj, C. (2023) · Elsevier eBooks · doi:10.1016/b978-0-323-99412-5.00003-4 · Cited by 8
Lagnaoui, S., En-Naimani, Z., & Haddouch, K. (2023) · Lecture notes in networks and systems · doi:10.1007/978-3-031-28387-1_22 · Cited by 7
Worddeepnet: handwritten gurumukhi word recognition using convolutional neural network
Kaur, H., Bansal, S., Kumar, M., Mittal, A., & Kumar, K. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-15527-2 · Cited by 6
“CNN is the neural network employed for image recognition and is designed in such a manner that it automatically and adaptively learns features hierarchy via a back-propagation algorithm [80, 89].”
MethodShaped-Charge Learning Architecture for the Human–Machine Teams
Galitsky, B. A., Ilvovsky, D., & Goldberg, S. I. (2023) · Entropy · doi:10.3390/e25060924 · Cited by 8
“In many domains, depending on how sophisticated the task is, DNN can outperform shallow neural networks that prevented fast training and building hierarchical models of complex training data [12].”
BackgroundMcDonnell, K. J. (2023) · Journal of Clinical Medicine · doi:10.3390/jcm12144830 · Cited by 7
“DNNs excel at discerning objects in images, but lack the ability to differentiate among similarly shaped objects with differentiating secondary characteristics [250,251].”
BackgroundKhuc, Q. V., & Tran, T. D. (2023) · Urban Science · doi:10.3390/urbansci7030084 · Cited by 6
“Deep learning algorithms have been shown to be very effective at a variety of tasks, including Deep learning algorithms have been shown to be very effective at a variety of tasks, including image recognition, natural language processing, and speech recognition [21,22].”
BackgroundNeighbor-Environment Observer: An Intelligent Agent for Immersive Working Companionship
Sun, Z., Liang, Q., Wang, M., & Zhang, Z. (2023) · ACM Symposium on User Interface Software and Technology (UIST) · doi:10.1145/3586183.3606728 · Cited by 6
“It is designed to deal with disruptions for people when they are immersed in a virtual working environment.”
BackgroundNew Materials and Devices for Thermoelectric Power Generation
Ismail, B. I. A. (2023) · IntechOpen eBooks · doi:10.5772/intechopen.110935 · Cited by 6
Wu, J., Han, W., Chen, J., & Wang, S. (2023) · Remote Sensing · doi:10.3390/rs16010053 · Cited by 6
Dynamic Electricity Price Forecasting via Deep Learning
Joshi, P. K., Størdal, S., Lien, G., Mishra, D., & Haugom, E. (2023) · IEEE International Conference on Energy Technologies for Future Grids (ETFG) · doi:10.1109/etfg55873.2023.10407554 · Cited by 6
“1) Initialization of Neural Network Weights: Generally, the predictions may fall in low-performance local-minima [11].”
BackgroundGanjkhani, M., Abbaspour, A., Fattaheian–Dehkordi, S., Gholami, M., & Lehtonen, M. (2024) · Sustainable Energy Grids and Networks · doi:10.1016/j.segan.2024.101335 · Cited by 10
“Therefore, the loss function in VAE consists of two parts: the mean squared error to minimize reconstruction error and another part modeled with KLD to ensure the compressed latent variable follows a Gaussian distribution [48].”
MethodClassification Feature Optimization for Global Wetlands Mapping
Yan, X., & Niu, Z. (2024) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2024.3382580 · Cited by 6
“However, some machine learning models, in particular deep neural networks, cannot be very well understood [54], [65]; the performance will vary depending on the architectures and hyper-parameter selection of the chosen algorithm [61], [80]; applying them globally is extremely hard [60].”
BackgroundUsing Deep Learning Algorithm in Security Informatics
Tahril, R., Lasbahani, A., Jarrar, A., & Balouki, Y. (2024) · International Journal of Innovative Science and Research Technology (IJISRT) · doi:10.38124/ijisrt/ijisrt24apr2271 · Cited by 6
“Another significant challenge is the interpretability and explainability of deep learning models, particularly in mission-critical applications where trust and transparency are paramount (Shrestha & Mahmood, 2019).”
BackgroundGultekin, E., & Aktaş, M. S. (2024) · International Journal of Software Engineering and Knowledge Engineering · doi:10.1142/s0218194024500396 · Cited by 6
Organ Contouring for Lung Cancer Patients with a Seed Generation Scheme and Random Walks
Cheng, D., Chi, J.-H., Yang, S.-N., & Liu, S.-H. (2020) · Sensors · doi:10.3390/s20174823 · Cited by 6
“A lot of deep learning methods [20,21] have been comp r based on many kinds of benchmarks [18,19,22,23]; for example, handwritten”
MethodAG-SGD: Angle-Based Stochastic Gradient Descent
Song, C., Pons, A., & Yen, K. K. (2021) · IEEE Access · doi:10.1109/access.2021.3055993 · Cited by 6
“Stochastic gradient descent (SGD) has been used in neural networks to minimize the cost for decades [4].”
MethodRao, A. S., & Mahantesh, K. (2021) · SN Computer Science · doi:10.1007/s42979-021-00589-6 · Cited by 6
Menegotto, A. B., & Cazella, S. C. (2021) · Studies in fuzziness and soft computing · doi:10.1007/978-3-030-70111-6_13 · Cited by 6
Channel Estimation-Free Deep Direct Beamforming With Low Complexity in mmWave Massive MIMO
Hong, Z., Li, T., Li, F., & Ju, R. (2021) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2021.3092600 · Cited by 6
“The stacked autoencoder can be seen as the combination of two normal autoencoders [35].”
BackgroundExpression Recognition Using Improved AlexNet Network in Robot Intelligent Interactive System
Zhao, Y., & Chen, D. (2022) · Journal of Robotics · doi:10.1155/2022/4969883 · Cited by 6
Reinforcement Learning of Causal Variables Using Mediation Analysis
Herlau, T., & Larsen, R. F. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i6.20648 · Cited by 7
“noise is an approach that underlies the most successful machine learning models today (Shrestha and Mahmood 2019).”
BackgroundHuman Detection and Biometric Authentication with Ambient Sensors
Andrews, J., & Li, J. (2022) · Springer eBooks · doi:10.1007/978-3-030-99383-2_2 · Cited by 6
Developing Novel Robust Loss Functions-Based Classification Layers for DLLSTM Neural Networks
Houran, M. A., Essai, M. H., Abdel-Raman, A. B., Badry, E. A., Hassan, A., & Atallah, H. A. (2023) · IEEE Access · doi:10.1109/access.2023.3275964 · Cited by 7
“This is because it does several difficult cognitive tasks as well as or better than humans’ performance [1].”
BackgroundA Comprehensive Survey on Content-Based Image Retrieval Using Machine Learning
Lande, M. V., & Ridhorkar, S. (2021) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-981-16-6285-0_14 · Cited by 7
Artificial Intelligence based Intrusion Detection System – A Detailed Survey
Sharma, V., Shah, D. J., Sharma, S. K., & Gautam, S. (2024) · ITM Web of Conferences · doi:10.1051/itmconf/20246504002 · Cited by 8
An Application of 3D Vision Transformers and Explainable AI in Prosthetic Dentistry
Sifat, F. A., Arian, M. S. H., Ahmed, S., Farook, T. H., Mohammed, N., & Dudley, J. (2024) · Applied AI Letters · doi:10.1002/ail2.101 · Cited by 5
Blind Interleaver Recognition Using Deep Learning Techniques
Ahamed, N., Swaminathan, R., & Naveen, B. (2024) · IEEE Access · doi:10.1109/access.2024.3476140 · Cited by 5
“In this sub-section, we have compared the classification accuracy of the proposed CNN and DRN models with other deep learning models such as autoencoder [47], FNN [48], and RNN [49] available in the literature.”
MethodHung, W., Baker, B., Campbell, P., Tang, Y., Ahmadov, R., Romero‐Alvarez, J., Li, H., & Schnell, J. L. (2025) · GeoHealth · doi:10.1029/2024gh001253 · Cited by 10
“The spread model is a convolutional autoencoder (CAE) model, a convolutional neural network (CNN; Yama-shita et al., 2018) as the main learning model coupled with autoencoder structure (Shrestha & Mahmood, 2019).”
Dynamic displacement reconstruction of bridge based on physics-informed recurrent neural network
Tao, Y., Chen, W., Li, Z., & He, W.-Y. (2025) · Advances in Bridge Engineering · doi:10.1186/s43251-025-00159-3 · Cited by 5
“This mechanism of RNN captures the temporal dependencies in sequence data, thereby enhancing the processing ability for time series data (Shrestha and Mahmood 2019; Karimpouli and Tahmasebi 2020).”
John, A. S. S., Alagendran, S., Sivaprakasam, B., Ramaswamy, M. K. M., Selvaraj, K., Ramanathan, S., Chokkalingam, P. V., Ravindran, N., & Suvaiyarasan, S. (2025) · World Academy of Sciences Journal · doi:10.3892/wasj.2025.363 · Cited by 6
Optimized Coupling Coil Geometry for High Wireless Power Transfer Efficiency in Mobile Devices
Alotaibi, F. M. (2025) · Journal of Low Power Electronics and Applications · doi:10.3390/jlpea15020036 · Cited by 5
Esmeray, H., Doğan, Z., & İşeri, İ. (2025) · Evolving Systems · doi:10.1007/s12530-025-09710-z · Cited by 6
“…Artificial Neural Networks (ANNs), Fuzzy Logic (FL), Support Vector Machines (SVMs), Fuzzy and Rough sets, Deep Learning (DL) and different hybrid methods have been used to analyze nonlinear signals (Mohanraj et al. 2022; Dhillon and Verma 2020; Maharana et al. 2022; Shrestha and Mahmood 2019).”
Gajula, M. K., Perumalla, S., Deepika, D. S., Dinesh, M. S., Giri, J. P., & Sabri, M. O. (2025) · International Conference on Networks and Cryptology (NETCRYPT) · doi:10.1109/netcrypt65877.2025.11102722 · Cited by 5
Dimitrova-Angelova, D., González, J. F. G., Carmona-Fernández, D., & Jaramillo-Morán, M. Á. (2025) · Applied Sciences · doi:10.3390/app15168883 · Cited by 5
Subramanya, V. K., Jiang, C., Bhat, C., Romario, Y. S., Li, X., & Ramezani, M. (2025) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-025-16376-z · Cited by 5
“The deep structure provides the ability to perform feature extraction and hierarchical learning, especially in fields like image recognition, language processing, and signal prediction [56, 57].”
Farman, H., Hussain, M. A., Hassan, S., Shaikh, S., & Ali, K. (2025) · Modeling Earth Systems and Environment · doi:10.1007/s40808-025-02630-6 · Cited by 5
“In this endeavor (Shrestha and Mahmood 2019), various optimization techniques that enhance the time a learner takes to complete their training while improving the effi - ciency of the training have also been discussed.”
Carneiro, G. A., Aubry, T., Cunha, A. M. T. D. S., Radeva, P. I., & Sousa, J. J. (2025) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2025.111134 · Cited by 8
Fan, J., Yao, Y., Li, Y., Zhang, X., Chen, J., Fisher, J. B., Zhang, X., Jiang, B., Liu, L., Xie, Z., et al. (2025) · Remote Sensing · doi:10.3390/rs17223665 · Cited by 5
Structural design and crashworthiness prediction of hybrid tubes
Lu, C., Liang, H., Wang, D., Wang, H., Li, H., & Chen, J. (2025) · International Journal of Mechanical Sciences · doi:10.1016/j.ijmecsci.2025.111096 · Cited by 5
Cakar, M., Insel, M. A., Sadikoglu, H., & Yücel, Ö. (2025) · Energy · doi:10.1016/j.energy.2025.139709 · Cited by 5
Diverse methods of incorporating physics into neural networks: A comprehensive review
Rajabi, M. M., Fahs, M., Bajgiran, M. M., Younès, A., & Lehmann, F. (2026) · Journal of Hydrology · doi:10.1016/j.jhydrol.2025.134903 · Cited by 7
An analytics-driven hybrid method for multi-item demand forecasting in supply chains
Lingkon, M. L. R., Hossain, M. S., & Chakrabortty, R. K. (2026) · Supply Chain Analytics · doi:10.1016/j.sca.2026.100194 · Cited by 5
Fernandes, T. B., Fernandes, E. C., & Borsato, M. (2026) · Journal of the Brazilian Society of Mechanical Sciences and Engineering · doi:10.1007/s40430-026-06408-4 · Cited by 5
“According to Shrestha and Mahmood [63] and Chen and Ran [14], Deep Neural Networks (DNNs) consist of multiple layers of interconnected nodes and can be applied to solve problems across various domains.”
Reinforcement Learning Model for Managing Noninvasive Ventilation Switching Policy
Feng, X., Wang, D., Pan, Q., Yan, M., Liu, X., Shen, Y., Fang, L., Cai, G., & Ning, G. (2023) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2023.3274568 · Cited by 5
“1, it utilizes the formal framework of Markov Decision Process (MDP) to define the interaction process between a learning agent and environment by means of states, actions and rewards [40].”
MethodDNN-Based Hospital Service Satisfaction Using GCNNs Learning
Song, Z., & Ma, S. (2023) · IEEE Access · doi:10.1109/access.2023.3289867 · Cited by 5
“utilizes a labeled sample of the collected data [15].”
BackgroundDynamic displacement estimation of structures using one-dimensional convolutional neural network
Zhou, X., & He, Y. (2023) · Frontiers in Physics · doi:10.3389/fphy.2023.1290880 · Cited by 5
Variational AutoEncoder Based CSI Feedback for Massive MIMO Systems
Swain, A., Hiremath, S. M., & Patra, S. K. (2023) · Wireless Personal Communications · doi:10.1007/s11277-023-10762-0 · Cited by 5
“Lately, the application of Deep Learning (DL) in diverse applications like computer vision, natural language processing, machine translation, and image processing [10], have demonstrated promising mechanism to handle complicated wireless communication systems [11].”
A deep learning based dynamic bandwidth allocation method for XG-PON based mobile fronthaul for CRAN
Garima, G., Jha, V., & Singh, R. K. (2024) · Computer Networks · doi:10.1016/j.comnet.2024.110344 · Cited by 5
A novel spectrogram based lightweight deep learning for IoT spectrum monitoring
Benazzouza, S., Ridouani, M., Salahdine, F., & Hayar, A. M. (2024) · Physical Communication · doi:10.1016/j.phycom.2024.102364 · Cited by 7
Anomaly Detection on Bridges Using Deep Learning With Partial Training
Santos-Vila, I., Soto, R., Vega, E., Peña, Á., & Crawford, B. (2024) · IEEE Access · doi:10.1109/access.2024.3447571 · Cited by 7
“On the other hand, the hidden layer, also known as the bottleneck, is where the AE represents the original data in a lower-dimensional latent space [44].”
BackgroundTomato Disease Detection Using Multispectral Imaging with Deep Learning Models
Silva, M. D., & Brown, D. (2024) · International Conference on Artificial Intelligence, Big Data, Computing and Data Communication Systems (icABCD) · doi:10.1109/icabcd62167.2024.10645256 · Cited by 5
“These models are designed to automatically learn patterns and relationships in data and make predictions based on these patterns [23].”
BackgroundTransmission line fault detection using deep learning technique
Hlalele, T. S. (2024) · International Conference on Advances in Artificial Intelligence (ICAAI) · doi:10.1145/3704137.3704170 · Cited by 6
“Several optimization methods were investigated to enhance the precision of the training[9].”
Ghosh, S., Saha, S., & Jana, N. D. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10890863 · Cited by 5
“Traditional deep learning models, often with complex architectures and many parameters, suffer from computational inefficiencies and scalability issues [7], [8].”
Xu, W., Li, C., Miao, X., & Liu, L. (2025) · BMC Psychology · doi:10.1186/s40359-025-02673-5 · Cited by 6
“Nonetheless, the progression of artificial intelligence has hastened, blurring the lines between humans and robots in terms of agency [54, 55].”
A deep learning pipeline to power infrastructure detection in high-resolution satellite images
Ye, M., Ward, P. J., Plaen, J. J.-F. G. D., & Koks, E. (2025) · Big Earth Data · doi:10.1080/20964471.2025.2490408 · Cited by 5
“This is largely attributed to the increasing availability of remote sensing data and the advancement of computational processing power, especially with the use of graphics processing units (GPUs) (Shrestha & Mahmood, 2019; Voulodimos et al., 2018).”
Meta-learning assisted robust control of universal quantum gates with uncertainties
Zhang, S., Miao, Z., Pan, Y., Tao, S., & Chen, Y. (2025) · npj Quantum Information · doi:10.1038/s41534-025-01034-9 · Cited by 5
“Since machine learning (ML) can efficiently and accurately complete classification or optimization tasks [11], the combination of ML and quantum engineering has been gradually explored [12, 13].”
Efosa-Zuwa, E., Oladipupo, O. O., & Oyelade, J. O. (2025) · Statistics Optimization & Information Computing · doi:10.19139/soic-2310-5070-2398 · Cited by 5
“In order to generate summaries with higher coherence and higher informativeness than existing retrieval–based methods, reinforcement learning and reward– based optimization have been applied [12].”
Lier, S. K., Eppers, T. M., Gerlach, J., Müller, P., & Breitner, M. H. (2025) · Electronic Markets · doi:10.1007/s12525-025-00802-x · Cited by 8
Deep double-pilot-based hybrid precoding in UAV-enabled mmWave massive MIMO
Hong, Z., Li, T., & Li, F. (2020) · EURASIP Journal on Wireless Communications and Networking · doi:10.1186/s13638-020-01854-7 · Cited by 5
Smart Home Load Analysis and LSTM-Based Short-Term Load Forecasting
Araya, S., Rakesh, N., & Kaur, M. (2021) · Advances in Science, Technology & Innovation/Advances in science, technology & innovation · doi:10.1007/978-3-030-66218-9_14 · Cited by 5
Mito, R., Kanno, K., Naruse, M., & Uchida, A. (2021) · Nonlinear Theory and Its Applications IEICE · doi:10.1587/nolta.13.123 · Cited by 5
“Deep learning has been intensively studied and exploited in various fields [1, 2].”
BackgroundRapid bacterial colony classification using deep learning
Akbar, S. A., Ghazali, K. H., Hasan, H. B., Mohamed, Z., Aji, W. S., & Yudhana, A. (2022) · Indonesian Journal of Electrical Engineering and Computer Science · doi:10.11591/ijeecs.v26.i1.pp352-361 · Cited by 6
“The beneficial of deep learning is proposed non-handcrafted approach [17].”
BackgroundLiu, X., Zhou, R., Qi, D., & Xiong, Y. (2022) · Mathematical Problems in Engineering · doi:10.1155/2022/2557865 · Cited by 6
Handwritten Digit Recognition using Deep Learning Networks
Yu, S., Liu, J., Shu, H., & Cheng, Z. (2022) · IEEE Conference on Telecommunications, Optics and Computer Science (TOCS) · doi:10.1109/tocs56154.2022.10016012 · Cited by 6
“With the emerging development of deep learning-based methods[1,2,3,4], many methods with novel backbones are proposed, such as AlexNet[5], VGG[6], ResNet[7], DenseNet[8], and inception[9] networks.”
MethodMusic Genre Classification by Machine Learning Algorithms
Zhang, X. (2023) · Highlights in Science Engineering and Technology · doi:10.54097/hset.v38i.5808 · Cited by 5
Deep learning for SDN-enabled campus networks: proposed solutions, challenges and future directions
Chanhemo, W. C., Mohsini, M. H., Mjahidi, M. M., & Rashidi, F. (2023) · International Journal of Intelligent Computing and Cybernetics · doi:10.1108/ijicc-12-2022-0312 · Cited by 6
Investigation of Machine Learning Models for Human Activity Recognition: A Comparative Study
Patel, A. D., Jhaveri, R. H., Shah, J. H., Patel, A. D., & Shah, K. A. (2023) · IEEE International Conference for Convergence in Technology (I2CT) · doi:10.1109/i2ct57861.2023.10126172 · Cited by 5
“Long short-term memory (LSTM) operates on the basis of the RNN structure, which comes under the category of feed-forward neural networks [30].”
BackgroundCovC-ReDRNet: A Deep Learning Model for COVID-19 Classification
Zhu, H.-R., Zhu, Z.-Q., Wang, S.-H., & Zhang, Y.-D. (2023) · Machine Learning and Knowledge Extraction · doi:10.3390/make5030037 · Cited by 4
“Generally speaking, a notable way to improve the performance of a model is to increase the depth of the network [60–63].”
BackgroundJoo, M. W., Ko, T., Kim, M. S., Lee, Y.-S., Shin, S. H., Chung, Y., & Lee, H. K. (2023) · Clinical Orthopaedics and Related Research · doi:10.1097/corr.0000000000002771 · Cited by 5
“The optimizer was Adam with a learning rate of 0.005, beta_1 of 0.9, and beta_2 of 0.99 [29].”
MethodInfluentialHan, S., Ye, Q., Hakamy, A., & Abd-Elnaiem, A. (2023) · Mechanics of Advanced Materials and Structures · doi:10.1080/15376494.2023.2195417 · Cited by 5
“Deep-learning (DL) is an important subclass of the ML methods developed based on employing at least three layers of perceptron [88].”
Zhu, W., Gui, R., & Guo, R. (2023) · Water-Energy Nexus · doi:10.1016/j.wen.2023.09.001 · Cited by 7
Goriya, M., Amrutiya, Z., Ghadiya, A., Vasa, J., & Patel, B. (2023) · Lecture notes in networks and systems · doi:10.1007/978-981-99-3758-5_42 · Cited by 5
Brain Tumor Classification using a Convolutional Neural Network and Different Optimizers
Mulla, M., & Direkoğlu, C. (2023) · Innovations in Intelligent Systems and Applications Conference (ASYU) · doi:10.1109/asyu58738.2023.10296659 · Cited by 5
“It is also known to improve the performance of neural networks by enabling faster convergence during the optimization process [1], [3], [8].”
BackgroundMethodInfluentialSenyuk, M. D., Safaraliev, M., Pazderin, A., Pichugova, O., Zicmane, I., & Beryozkina, S. (2023) · Mathematics · doi:10.3390/math11224667 · Cited by 6
Human Activity Recognition by BiLSTM Recurrent Neural Networks and Support Vector Machine
Ridha, A. A., Almaameri, I. M., Blázovics, L., & Abbas, H. M. (2023) · International Conference on Engineering Technology and its Applications (IICETA) · doi:10.1109/iiceta57613.2023.10351372 · Cited by 7
“Deep learning contains many important algorithms, one widely used from this algorithm is Recurrent Neural Networks (RNN) [12].”
MethodApplications of Machine Learning in Mobile Networking
Shnain, A. H. (2023) · Journal of Smart Internet of Things · doi:10.2478/jsiot-2023-0009 · Cited by 5
Li, W., Yan, W., Shi, H., Li, S., & Zhou, Y. F. (2024) · International Conference on Control Engineering and Artificial Intelligence (CCEAI) · doi:10.1145/3640824.3640843 · Cited by 5
“Deep Reinforcement Learning (DRL) combines deep learning and reinforcement learning, and has the ability to perceive high-dimensional data [21] and strong decision-making ability [20].”
BackgroundNursamsi, I., Sonter, L. J., Luskin, M. S., & Phinn, S. (2024) · International Journal of Applied Earth Observation and Geoinformation · doi:10.1016/j.jag.2024.104015 · Cited by 5
Deep Learning-Based Self-Adaptive Evolution of Enzymes
Jiang, S., & Yi, D. (2024) · Pharmaceutical Fronts · doi:10.1055/s-0044-1788317 · Cited by 5
Akgül, A., Deniz, E., Emi̇n, B., ÇİZMECİ, H., Alaca, Y., Akmeşe, Ö. F., & Özdem, S. (2024) · The European Physical Journal Special Topics · doi:10.1140/epjs/s11734-024-01329-6 · Cited by 5
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
