Convolutional Neural Networks: A Survey
Open accessThe DOI matches its Crossref record; 199 of the 199 references it cites were found in a registry or an index.
Abstract
Artificial intelligence (AI) has become a cornerstone of modern technology, revolutionizing industries from healthcare to finance. Convolutional neural networks (CNNs) are a subset of AI that have emerged as a powerful tool for various tasks including image recognition, speech recognition, natural language processing (NLP), and even in the field of genomics, where they have been utilized to classify DNA sequences. This paper provides a comprehensive overview of CNNs and their applications in image recognition tasks. It first introduces the fundamentals of CNNs, including the layers of CNNs, convolution operation (Conv_Op), Feat_Maps, activation functions (Activ_Func), and training methods. It then discusses several popular CNN architectures such as LeNet, AlexNet, VGG, ResNet, and InceptionNet, and compares their performance. It also examines when to use CNNs, their advantages and limitations, and provides recommendations for developers and data scientists, including preprocessing the data, choosing appropriate hyperparameters (Hyper_Param), and evaluating model performance. It further explores the existing platforms and libraries for CNNs such as TensorFlow, Keras, PyTorch, Caffe, and MXNet, and compares their features and functionalities. Moreover, it estimates the cost of using CNNs and discusses potential cost-saving strategies. Finally, it reviews recent developments in CNNs, including attention mechanisms, capsule networks, transfer learning, adversarial training, quantization and compression, and enhancing the reliability and efficiency of CNNs through formal methods. The paper is concluded by summarizing the key takeaways and discussing the future directions of CNN research and development.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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
“Finally, RobotReviewer/RobotSearch employs an ensemble classifier, combining multiple CNN models (Krichen 2023) and soft-margin Support Vector Machines (Boser et al. 1992) in order to categorise articles based on their risk of bias assessment (either low or high/unclear) and concurrently extract sentences that substantiate these judgements.”
From Artificial intelligence for literature reviews: opportunities and challenges (2024) · cites this paper as Krichen 2023
Citations
Cites
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
PyTorch: An Imperative Style, High-Performance Deep Learning Library
Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., et al. (2019) · arXiv · doi:10.48550/arxiv.1912.01703 · Cited by 31,473
Recent advances in convolutional neural networks
Gu, J., Wang, Z., Kuen, J., Ma, L., Shahroudy, A., Shuai, B., Liu, T., Wang, X., Wang, G., Cai, J., et al. (2018) · Pattern Recognition · doi:10.1016/j.patcog.2017.10.013 · Cited by 6,576
A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects
Li, Z., Liu, F., Yang, W., Peng, S., & Zhou, J. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3084827 · Cited by 5,273 · cited 1×
“Convolutional neural networks (CNNs) [14–16] are a popular type of ML model that have been widely utilized for various tasks, including image recognition [17–20], speech recognition [21–25], and NLP [26–30].”
Understanding of a convolutional neural network
Albawi, S., Mohammed, T. A., & Al-Zawi, S. (2017) · 2017 International Conference on Engineering and Technology (ICET) · doi:10.1109/icengtechnol.2017.8308186 · Cited by 3,986 · cited 1×
“Convolutional neural networks (CNNs) [14–16] are a popular type of ML model that have been widely utilized for various tasks, including image recognition [17–20], speech recognition [21–25], and NLP [26–30].”
Deep Convolutional Neural Networks for Image Classification: A Comprehensive Review
Rawat, W., & Wang, Z. (2017) · Neural Computation · doi:10.1162/neco_a_00990 · Cited by 3,503
Chen, Y., Jiang, H., Li, C., Jia, X., & Ghamisi, P. (2016) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2016.2584107 · Cited by 2,984
Artificial intelligence and the future of work: Human-AI symbiosis in organizational decision making
Jarrahi, M. H. (2018) · Business Horizons · doi:10.1016/j.bushor.2018.03.007 · Cited by 2,772
Duan, Y., Edwards, J. S., & Dwivedi, Y. K. (2019) · International Journal of Information Management · doi:10.1016/j.ijinfomgt.2019.01.021 · Cited by 2,628
Attention mechanisms in computer vision: A survey
Guo, M.-H., Xu, T.-X., Liu, J.-J., Liu, Z.-N., Jiang, P.-T., Mu, T.-J., Zhang, S.-H., Martin, R. R., Cheng, M.-M., & Hu, S.-M. (2022) · Computational Visual Media · doi:10.1007/s41095-022-0271-y · Cited by 2,566 · cited 1×
“Attention mechanisms are a powerful tool for improving the performance of CNNs [178–182].”
Research works printed but not linked: 9
- Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning, MIT Press.
- Bengio, Y., Goodfellow, I., and Courville, A. (2017). Deep Learning, MIT Press.
- Gan, 2019, Research of facial beauty prediction based on deep convolutional features using double activation layer, Acta Electonica Sin., 47, 636
- Simon, 2019, Shallow cnn with lstm layer for tuberculosis detection in microscopic images, Int. J. Recent Technol. Eng., 7, 56
- Ndong, P.S.B., Adoni, W.Y.H., Nahhal, T., Kimpolo, C., Krichen, M., Byed, A.E., Assayad, I., and Mutombo, F.K. (2021). Advances on Smart and Soft Computing: Proceedings of ICACIn 2021, Springer.
- Mehdi, C.A., Nour-Eddine, J., and Mohamed, E. (2022, January 22–27). Regularization in CNN: A Mathematical Study for L 1, L 2 and Dropout Regularizers. Proceedings of the International Conference on Advanced Intelligent Systems for Sustainable Development, Rabat, Morocco. · DOI
- Moolayil, J., Moolayil, J., and John, S. (2019). Learn Keras for Deep Neural Networks, Springer. · DOI
- Wu, P. (2021-, January 27). PyTorch 2.0: The Journey to Bringing Compiler Technologies to the Core of PyTorch (Keynote). Proceedings of the 21st ACM/IEEE International Symposium on Code Generation and Optimization, Virtual.
- Rundong, 2022, Multidimensional Linear Data Processing Based on OpenCL Kernel Function in MXNet Framework, Front. Data Domputing, 4, 29
Cited by
Items 601–700 of 869
The application of deep learning studies in cancer diagnosis
Huang, H. (2025) · International Conference on Machine Learning, Neural Networks, and Computer Software (MLNNCS) · doi:10.1117/12.3092609
“[17] 4.3 The F1-Score represents the harmonic mean of precision and recall, serving as a single, balanced indicator of a model’s performance.”
InfluentialA Comparative Study of CNN and MI-CNN for Enhancing Traffic Injury Severity Prediction
Chaw, K. E. E., & Lwin, M. M. (2025) · International Conference on Advanced Information Technologies (ICAIT) · doi:10.1109/icait68809.2025.11236780
“CNN consists of 1D convolutional layers (Conv1D) that extract patterns across feature dimensions, pooling layers (MaxPooling1D) that downsample the data and reduce overfitting, and fully connected (Dense) layers to classify or regress traffic injury severity [5, 10].”
RLSE Aktivasyon Fonksiyonu Tasarımının Derin Sinir Ağlarının Performansındaki Etkisi
Özeloğlu, İ. G., Aydın, E. A., & Barışçı, N. (2025) · Journal of Polytechnic · doi:10.2339/politeknik.1601441
ADMM-Enhanced CNN Training Framework With Global Convergence Guarantees
Song, C., Kong, Z., Liu, S., Ding, L., Huang, B., Xiang, W., & Huang, T. (2025) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2025.3636117
“The most widely used methods for training CNNs are stochastic gradient descent (SGD) and its variants [10], such as Adagrad [11], AMSGrad [12], and Adam [13].”
App2: Model for apple leaf disease detection based on deep learning
Aronès, E., Espinal, J., & Salas, C. (2025) · International Conference on Intelligent Systems, Metaheuristics & Swarm Intelligence (ISMSI) · doi:10.1145/3760622.3760653
“The CNN algorithm was designed with TensorFlow [31], a library for implementing deep learning models.”
Saha, T., & Santra, S. (2025) · International Journal of Preventive Medicine and Health · doi:10.54105/ijpmh.d1089.06011125
Winiarti, S., Sunardi, S., & Fadhil, A. (2025) · International Journal of Informatics and Computation · doi:10.35842/ijicom.v7i1.116
HE, P., Cheng, X., Wen, X., YI, Y., ZOU, Y., MAO, Z. F., CHEN, Z. L., & Chen, Y. (2025) · Applied Ecology and Environmental Research · doi:10.15666/aeer/2306_1073510749
Farej, Z. K., & MohammedSami, Z. M. (2025) · International Conference on Business Analytics for Technology and Security (ICBATS) · doi:10.1109/icbats66542.2025.11258550
“The max pooling layer reduces the spatial dimensions of the input by taking the maximum value over a defined window, thus down-sampling the input while retaining important features as in equation [29]: (6) Where pool operation takes maximum over spatial window.”
Diagnostic Accuracy Comparison of Ml Based on Performance Analysis
Hazarika, K., Gupta, K. K., Priytam, A., Bisht, S., Verma, Y., & Trivedi, V. (2025) · doi:10.1109/cises66934.2025.11265467
“Illustration are of rapid advancements in convolutional neural networks and AI in the healthcare space suggesting fast gains in imaging processing can outperform the human eye for recognition capability [3][4][9][10][12].”
Performance Assessment of Object Detection for Military Vehicles in Complex Visual Environments
Hildebrand, F. K., Schnell, M. K., Bachmann, E., & Sahutoglu, Z. (2025) · International Conference on Electrical Engineering, Computing Science and Automatic Control (CCE) · doi:10.1109/cce67728.2025.11271927
“These limitations underscore the importance of adopting advanced methodologies like Convolutional Neural Networks (CNNs) to achieve efficient and accurate object detection in these critical applications [4].”
Syarifah, U. M., Nugraha, A., Luthfiarta, A., Dewi, I. N., Mumtaz, N. A., & Fitri, M. (2025) · International Seminar on Application for Technology of Information and Communication (iSemantic) · doi:10.1109/isemantic67418.2025.11292113
“ResNet-50 and InceptionV3 were included as foundational models to directly compare against the baseline study and to evaluate their respective approaches of deep residual learning versus multi-scale feature extraction [17].”
Sun, X., LI, Y. G., Zhai, X., Zhang, S., Guo, Y., & Tian, W. (2025) · EURASIP Journal on Advances in Signal Processing · doi:10.1186/s13634-025-01281-0
“This complexity manifests as non-convexity in the log-posterior landscape—evidenced by numerous local optima—which fundamentally precludes guaranteed convergence to global solutions through direct numerical optimization [29].”
Using Artificial Intelligence Algorithms to Recognize Osteoporosis: A Review
Razzaq, S. A., & Khaleel, B. I. (2024) · Optimum: Journal of Economics and Development (University of Ahmad Dahlan Yogyakarta) · doi:10.26555/jiteki.v10i4.30352
Segmentacija CT slik s postopki umetne inteligence z orodjem Monai Label in programom 3D-Slicer
Oletič, D. (2024) · Repository of the University of Ljubljana (University of Ljubljana)
Softwarové prostředí pro automatickou detekci fokálních kortikálních dysplázií
Kovaříčková, D. (2024) · DSpace VŠB-TUO (VŠB-TUO)
Sadeghikhah, K. (2024) · oURspace (University of Regina) · doi:10.82465/5396
Time-Series Data Analysis in Biomedical Applications
Wang, Y. (2024) · MacSphere (McMaster University) · doi:10.71548/15541
Silvia, R. (2024) · Digilib Repository Unila (Lampung University)
Zhang, Z. D., Liu, M., & Zhang, Y. (2025) · International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD) · doi:10.1109/icnc-fskd67701.2025.11198119
Прокопенко, М. Е. (2023) · Electronic Sumy State University Institutional Repository (Sumy State University)
Metal work-pieces sorting method based on the convolutional neural networks
Zhang, X., & Jiang, Y. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.113038
Control of Semiactive Suspension Systems Using Preview Information and Convolutional Neural Networks
Zhu, Y., Zhang, X., Yin, Y., Jiang, Q., Zhang, H., Yang, M., & Yan, X. (2025) · Shock and Vibration · doi:10.1155/vib/9979010
“Currently, the common CNN models based on target classifcation mainly include the following networks [48]: AlexNet, VGGNet [49], Google InceptionNet, and ResNet [50].”
The Impact of Loss Function Topology on Gradient Descent
Skudnig, R. (2025) · ISU Red - Research and eData (Illinois State University) · doi:10.30707/etd.1763755358.338765
Analyse des données de réflectance du proche infrarouge basée sur les réseaux de neurones profonds
Abela Nomo, S. G. (2024) · e-Theses (Université du Québec à Trois-Rivières)
Threats of modern technologies in the context of public management
Berkowicz, A. (2025) · Jagiellonian University Repository (Jagiellonian University)
Optimering av Talarverifieringsmodeller för Resursbegränsade Enheter
Lindberg, A. (2025) · DiVA (Digitala Vetenskapliga Arkivet)
Tafti, K. T. (2025) · eScholarship@McGill (McGill) · doi:10.82308/51435
Shahverdi, V. (2025) · DiVA (Digitala Vetenskapliga Arkivet)
Загородний, С. С., & Zagorodnii, S. S. (2025) · Electronic scientific archive of UrFU (Ural Federal University)
A Deep Learning Pipeline for Accurate Road Detection in Satellite Imagery
Mayouche, I., Boukrouh, I., & Azmani, A. (2025) · International Journal of Engineering · doi:10.5829/ije.2026.39.09c.04
EMOTION RECOGNITION IN DIGITAL ART USING DEEP LEARNING
Suryavanshi, A., Sharma, N., Chandna, M., Swarup, L., Ms. Sunitha, B. K., & Karthick, S. (2025) · ShodhKosh Journal of Visual and Performing Arts · doi:10.29121/shodhkosh.v6.i3s.2025.6779
MACHINE VISION FOR SCULPTURE SURFACE OPTIMIZATION
Bhan, S., Khan, A. K., Kumar, V., Jagga, M., Megala, G., Ramtirthkar, C. R., & Yadav, J. P. (2025) · ShodhKosh Journal of Visual and Performing Arts · doi:10.29121/shodhkosh.v6.i4s.2025.6861
Pajura, I., & Korga, S. (2025) · Journal of Computer Sciences Institute · doi:10.35784/jcsi.8020
“Deep CNNs effectively capture features at various levels of abstraction [3], integrating them in a comprehensive manner from input to output, which is a characteristic feature of multilayer architectures, as highlighted in [5] and [6].”
APPLYING MODERN CNN ARCHITECTURES TO BUILD AN EFFECTIVE FACE DETECTION MODEL
Hasobe, N. N. (2025) · International Journal of Apllied Mathematics · doi:10.12732/ijam.v38i12s.1575
“The scope of deep learning based image and video object detection systems is continuously augmenting [2] because of the vast possibilities of automation provided by artificial intelligence.”
Multimodal AI Application for Vietnamese Digital Learning Material Classification
Giang, M. N., Nguyen, Q., & Tran, H. (2025) · World Journal of Engineering and Technology · doi:10.4236/wjet.2026.141006
Barradas-Palmeros, J.-A., Mezura‐Montes, E., Acosta‐Mesa, H., Lόpez-Herrera, C.-A., & Hernández-Somohano, F.-J. (2025) · Mexican International Conference on Computer Science · doi:10.1109/enc68268.2025.11311921
“The leading cause of their success is related to their capacity to hierarchically extract spatial features from the images using the convolution operation [1].”
Vertical Federated Convolutional Framework Based on Function Secret Sharing
Teng, L., Feng, Q. B., Luo, M., & He, D. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-6209-1_12
Al-Rifai, O. H., & Yusof, S. A. M. (2026) · Studies in computational intelligence · doi:10.1007/978-3-032-00232-7_60
Shifare, H. L., Shukla, M., Kothari, N. H., Kehali, B., Kedre, S., & Demissie, M. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-08253-4_35
Applications of Matrices in Computer Graphics and Image Processing
Sharma, D. N. (2020) · Journal of Mathematical Problems Equations and Statistics · doi:10.22271/math.2020.v1.i2a.277
Metallinos, A. S., Chondros, M. K., Papadimitriou, A. G., & Tsoukala, V. K. (2026) · Journal of Marine Science and Engineering · doi:10.3390/jmse14020110
Beyond accuracy: Reliability and uncertainty estimation in convolutional neural networks
Ruijs, S., Kosiakova, A., & Javed, F. (2026) · Neurocomputing · doi:10.2139/ssrn.6030753
Applications of artificial neural networks in photovoltaics systems
Τζιάτζιου, Δ. Α. (2025) · University of Thessaly Institutional Repository (University of Thessaly)
Comparative Study of Lightweight Deep Learning Models for Soccer Penalty Kick Image Classification
Su, G., Liang, Z., Wang, C., & Wong, D. (2025) · International Conference on Digital Society and Intelligent Systems (DSInS) · doi:10.1109/dsins68311.2025.11329933
“Recent advances in deep learning, particularly convolutional neural networks (CNNs) [3-4], have made it possible to automatically extract discriminative features from raw images and achieve remarkable improvements in image classification tasks.”
Motion-intensity estimation for upper limb exoskeletons: Optimizing support for dynamic assistance
Zafalon, G. (2024) · Aaltodoc (Aalto University)
Zarei, A. R. (2026) · Environmental and Sustainability Indicators · doi:10.1016/j.indic.2026.101133
Intelligent System for Recognizing Human Faces Using Deep Learning Techniques
Hasobe, N. N., Anwar, H. M., & Ahmed, Z. O. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-14189-7_24
Rozada, A., Baroroh, N., Rizky, M. I. K., & Pramunendar, R. A. (2025) · Jurnal Sistem Komputer dan Informatika (JSON) · doi:10.30865/json.v7i2.9389
“Persamaan ini menggambarkan proses penjumlahan hasil perkalian antara nilai masukan dan bobot dalam jendela konvolusi 3x3[27].”
Yabani, M., Faisal, M. R., Indriani, F., Nugrahadi, D. T., Kartini, D., & Satou, K. (2026) · Journal of Electronics Electromedical Engineering and Medical Informatics · doi:10.35882/jeeemi.v8i1.1256
Thapa, B. B. (2026) · Himalayan Journal of Applied Science and Engineering · doi:10.3126/hijase.v6i2.90254
“Convolutional layers enforce local connectivity by linking each neuron only to a small receptive field of the previous layer and apply weight sharing across spatial locations to extract hierarchical features from structured inputs such as images [2].”
Dai, P. (2025) · Repositori digital de la UPF (Universitat Pompeu Fabra)
Öztürk, S. (2026) · Uludağ Üniversitesi Fen Edebiyat Fakültesi Sosyal Bilimler Dergisi · doi:10.21550/sosbilder.1744064
Comparative evaluation of AlexNet, SqueezeNet, VGG16, and ResNet50 for gender and hijab detection
Supriyanto, A., Wismarini, T. D., Februariyanti, H., Jananto, A., Damaryanti, F., & Satria, H. N. (2026) · Bulletin of Electrical Engineering and Informatics · doi:10.11591/eei.v15i1.9936
“This process used a confusion matrix as recommended by Krichen [27], to obtain metrics such as accuracy, precision, recall, and F1-score for the CNN architectures tested.”
Josylin, T. M., Shidaganti, G. I., Dasegowda, V., Jadagerimath, A. N., & Sheelvanthmath, P. (2026) · Bulletin of Electrical Engineering and Informatics · doi:10.11591/eei.v15i1.10789
“CNN [24] is a type of deep learning model that is specifically developed for processing structured grid data such as images.”
Flexible Solar Panel Recognition Using Deep Learning
Sun, M., & Nguyen, D. H. (2026) · Energies · doi:10.3390/en19040872
Evaluation of engagement in online learning: insights based on human factor analysis
Park, S., Jeong, B., Son, W., Lee, C., & Jeong, Y. (2026) · The Journal of Supercomputing · doi:10.1007/s11227-026-08298-8
“Furthermore, online learners often participate in uncontrolled environments with diverse backgrounds, which makes frame-based algorithms prone to inaccuracies in evaluating engagement due to irrelevant background patterns [17].”
Deep Learning for Plant Leaf Disease and Stress Detection
Radi, M., Dehbi, I., Ikan, C., Soussani, F.-E., Achetoui, H., Meddich, A., & Lahlali, R. (2026) · CABI biotechnology series. · doi:10.1079/9781836991120.0004
FARIA, A. S., da Silva, R. J., Montenegro, P. A., Faria, L. T., Lopes, M. L. M., Lotufo, A. D. P., & MINUSSI, C. R. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6263106
FARIA, A. S., da Silva, R. J., Montenegro, P. A., Faria, L. T., Lopes, M. L. M., Lotufo, A. D. P., & MINUSSI, C. R. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6263100
Deng, Z., Feng, L., Jia, S., & Xu, B. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.109870
Comparison of image enhancement methods for pratima theft detection using artificial intelligence
Sudarma, M., Ariyani, N. W. S., Udayana, I. P. A. E. D., Pranatayana, I. B. G., & Jasa, L. (2026) · IAES International Journal of Artificial Intelligence · doi:10.11591/ijai.v15.i1.pp213-228
“Their training relies on backpropagation, while forward propagation is used during classification [29].”
A Research on Depthwise Separable Convolution Accelerator Based on Tensor Permutation
An, G., Jiang, Z., Kou, J., Wu, M., & Huang, Y. (2025) · International Conference on Robotics, Intelligent Control and Artificial Intelligence (RICAI) · doi:10.1109/ricai68060.2025.11385146
“In recent years, with the continuous improvement of hardware performance, neural network technology has achieved remarkable progress[1].”
Bonfini, P., Schetakis, N. A., Sukhnandan, J., Drosopoulos, G. Α., & Stavroulakis, G. Ε. (2026) · Materials · doi:10.3390/ma19050878
“Among ML models, Convolutional Neural Networks (CNNs) are specifically designed to work with images: they hierarchically extract features, progressing from low-level local pixel patterns to high-level semantic representations [27].”
TC-EEGNet: A Temporal Convolution Enhanced EEGNet for EEG Based Alcohol Addiction Classification
Li, Y., & Wang, J. (2025) · International Conference on Image, Signal Processing and Communication Technology (ISPCT) · doi:10.1109/ispct68220.2025.11406858
“The overall framework, inspired by the classical EEGNet architecture, integrates the feature extraction efficiency of convolutional neural networks (CNN) [5,6] with enhanced temporal modeling capability through an additional temporal convolutional module.”
Pérez–Enríquez, L., Martinez, S. Z., Altamirano-Robles, L., Hernández, R. D., & Velázquez-Arreola, J. D. J. (2026) · Earth · doi:10.3390/earth7020034
Software Quality Assurance Techniques of Models and Practices
Subbaiah, E. (2020) · Computer Science Engineering and Technology · doi:10.46632/cset/2/4/6
SBMN: Similarity-Based Memory Network for the Diagnosis of Vertical Root Fracture in Dental Imaging
Wang, J., Jin, X. Y., Zhang, Y. F., Yuan, J., Lin, Z. T., & Chen, Y. (2026) · Diagnostics · doi:10.3390/diagnostics16050710
Technology-Based Classification of Clerodendrum Paniculatum Using CNN and Confusion Matrix
Wijaya, P. (., Makarim, A. R., Muhammad, M. A. (., Febriyani, C. (., Hidayatullah, V., & Annisa, R. N. (. ). (2024) · Neliti
Hwang, S., & Jang, S. B. (2026) · International Journal on Advanced Science Engineering and Information Technology · doi:10.18517/ijaseit.16.1.21542
Jayanthi, G., & Brindha, S. (2026) · Journal of Electrical Engineering and Technology · doi:10.1007/s42835-026-02711-1
Amina, G., Bougherara, M., & Amara, R. (2026) · IAES International Journal of Robotics and Automation (IJRA) · doi:10.11591/ijra.v15i1.pp136-148
A Dynamic Speech Enhancement Algorithm Based on Spectral Masking
Wu, Y., Min, Y., & Xu, C. (2025) · International Academic Exchange Conference on Science and Technology Innovation (IAECST) · doi:10.1109/iaecst68792.2025.11415122
“Among these, Convolutional Neural Networks [4] (CNN) are widely favored due to their small model size and fast computational speed.”
Junior, M. A. M. D. F., & Fernandes, R. A. S. (2026) · Electronic System of Publishing Periodicals (Federal University of Rio Grande do Sul) · doi:10.22456/2175-2745.150976
LDDm-YOLO: A Distilled YOLOv8 Model for Efficient Real-Time UAV Detection on Edge Devices
Salisu, M. L., & Musa, A. (2026) · International Electronic Conference on Applied Sciences (ASEC) · doi:10.3390/engproc2026124068
Yedage, S. L., & Tripathi, D. M. (2025) · International Journal of Scientific Research in Science Engineering and Technology · doi:10.32628/ijsrset261346
Controlo energético de GPU em sistemas de Deep Learning
Rodrigues, D. A. M. A. (2025) · Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT)
Optimised deep learning for oral cancer classification
Sulochana, C., & Sumathi, M. (2026) · Acta Polytechnica · doi:10.14311/ap.2026.66.0098
“Specialists in otolaryngology and dentistry are responsible for diagnosing and treating this condition, which is regarded as the sixth most prevalent form of cancer globally [5].”
Pradeep Kumar, G., Rekha, R., Ganga, S., Al-Safarini, M. Y., Nishitha, P., & Karthikeyan, G. (2025) · International Conference on Advances in Computation, Communication and Information Technology (ICAICCIT) · doi:10.1109/icaiccit68829.2025.11434315
“Recurrent Neural Networks, like Long Short-Term Memory (LSTM) networks, are being applied to represent time-series data and to predict the remaining useful life (RUL) of components [15,16].”
Джураева, Р. С. (2025) · Электронный архив ЮУрГУ (South Ural State University)
Emotion Recognition in Children Using Lightweight Deep Learning Model for Mobile Applications
Ramzan, H. A., Asad, S. M., Monim, R. M., Rauf, M., Zainab, Y., & Awais, M. (2025) · IEEE International Conference on Future Machine Learning and Data Science (FMLDS) · doi:10.1109/fmlds67896.2025.00045
“The suggested system uses a robust Convolutional Neural Network (CNN) [11] model developed to trade accuracy and efficiency of computation while being apt for use on mobile devices.”
Gas Insulated Switchgear Defect Detection Method Based on Improved RT-DETR
Huang, M., Xu, G., Bai, X., Li, W., & Ding, H. (2025) · IEEE International Conference on Computer and Communications (ICCC) · doi:10.1109/iccc68654.2025.11437672
“Significant advancements have been made in the field of image detection using deep learning technologies, particularly with the application of Convolutional Neural Networks (CNN[1]) and Transformer[2] architectures in object detection.”
Neural Network Method for Determining Sanctions’ Impact on the Administrative Offence Level
Vladov, S., Vysotska, V., Voloshanivska, T. V., Podorozhnii, Y. Y., Hanenko, I., Nazarkevych, M., Hovorov, V., Shopina, I. M., Zherebtsov, D., & Pitomets, A. (2026) · Applied Sciences · doi:10.3390/app16073340
Imbalanced network attack class classification using an ensemble machine learning approach
Hui, F. S. (2024) · Institutional Repositories DataBase (IRDB) · doi:10.34429/0002000283
Wu, J., Li, R., Di, L., Ji, Y., Zheng, Y., & Huang, L. (2025) · International Conference on Computer Science and Management Technology (ICCSMT) · doi:10.1145/3795154.3795354
“For map image element inspection, optimized convolutional neural network (CNN) algorithms [ 11 – 14 ] may be employed.”
Deep Learning-Based Classification of UAV Orthophotos Using MIDNet Architecture
Aslan, İ., & Polat, N. (2026) · DergiPark
Convolutional Neural Networks: Operation Principles and Applications
Yu, H., Sun, P., Ding, B., & Halak, B. (2025) · Springer eBooks · doi:10.1007/978-3-032-08514-6_1
Un framework sécurisé et intelligent pour la gestion des drones
Tlili, F. (2024) · theses.fr (ABES) · doi:10.70675/10b72e6aze1b4z4255z8bbcz87de461f9867
Deng, B., Ren, L., Chan, T., & Tang, C. (2026) · Scientific Reports · doi:10.1038/s41598-026-46316-0
Gaddipati, S. S. (2024) · World Journal of Advanced Research and Reviews · doi:10.30574/wjarr.2024.22.2.1509
Comparative Performance Analysis in Melanoma Detection with DeepLabV3+ Segmentation
Pranata, C. N., Halim, P. M., Dewi, C. A., & Harefa, J. (2025) · International Conference on Computer and Communication Engineering · doi:10.1109/iccce66530.2025.11473999
“ResNet enabled very deep networks through residual connections [16], while DenseNet improved feature reuse by linking each layer to all others [11].”
Advancements in Deep Learning for Multi-disease Detection in Medical Imaging
Addouni, F. E., Ahkouk, K., Aaoud, H. E., & Moubtahij, H. E. (2026) · Advances in Science, Technology & Innovation/Advances in science, technology & innovation · doi:10.1007/978-3-031-97825-8_79
Βελτίωση εικόνας ανά στάδιο για βαθμονόμηση διαβητικής αμφιβληστροειδοπάθειας
Roumeliotis, I. (2026) · DSpace - NTUA (National Technical University of Athens) · doi:10.26240/heal.ntua.31949
Solar Flare Detection from Sudden Ionospheric Disturbances in VLF Signals via a CNN–HMM Framework
Velchev, Y. S., Bonev, B. G., Iliev, I. G., Gallagher, P. T., Petkov, P. Z., & Nachev, I. (2026) · Sensors · doi:10.3390/s26082548
“Beyond detection algorithms tailored to a specific imager, CNNs [25] have been broadly applied for solar flare classification and prediction from magnetic field data and multi-wavelength imagery.”
Vision-Language Models for Automatic Feature Recognition with Limited Training DataPreprint
Corney, J., Li, S., & Shang, Z. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6626307
Facial recognition using transfer lerning and neural networks
Silva, J. C. R. (2023) · Institutional Repository of the Federal Technological University of Paraná (RIUT) (Federal University of Technology – Paraná)
Wang, T., Tan, W., Luo, Z., Wang, Y. P., & zhao, Y. (2026) · Signal Image and Video Processing · doi:10.1007/s11760-026-05308-3
“Notably, convolutional neural networks (CNN) are effective at automatically extracting local features and fitting complex nonlinear mappings, with demonstrated success in image, speech, and time-series tasks [24–27].”
Rosyidiin, A. F., Singgih, M. L., & Sudiarno, A. (2026) · Evergreen · doi:10.5109/7420072
Metadata
- Authors
- Krichen, M.
- Affiliations
- University of Sfax (TN)
- Corresponding author
- Krichen, Moez
- ORCID
- Krichen, Moez
- Venue
- Computers
- Publisher
- MDPI AG
- Published
- 2023-07-28
- Volume
- 12
- Issue
- 8
- Pages
- 151
- ISSN
- 2073-431X (ISSN-L)
- OpenAlex
- W4385342469
- Cited by
- 623
- References
- 199
- Citations by year
- 2026: 144 · 2025: 242 · 2024: 189 · 2023: 48
- FWCI
- 56.55
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Computers (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Keywords
- convolutional neural networks, image recognition, convolutional neural network architecture, LeNet, AlexNet, VGG, ResNet, InceptionNet, activation functions, hyperparameter optimization, deep learning libraries, attention mechanism, capsule networks, transfer learning, adversarial training, model compression, formal verification
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
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.