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 301–400 of 869
Cheng, H. D., Zhang, J., Yan, H., Wang, Y., & Dong, L. (2025) · Multiscale and Multidisciplinary Modeling Experiments and Design · doi:10.1007/s41939-025-00950-9 · Cited by 4
“More recently, convolutional neural networks (CNNs) (Song et al. 2019; Zhang et al. 2022; Gopalakrishnan et al. 2017; Krichen 2023; Aloysius et al. 2017) have emerged as a powerful tool in road distress detection.”
AI-Computing Through Low-Consumption VCSEL-based Analog Radio-over-Fiber System
Nanni, J., Wang, S., Benlarbi‐Delaï, A., & Tartarini, G. (2025) · International Topical Meeting on Microwave Photonics · doi:10.1109/mwp65272.2025.11371802 · Cited by 4
“Non-linear functions play in fact a key role in AI-computing [3] as neuron activation functions allowing efficient computation.”
SNR and Resource Adaptive Deep JSCC for Distributed IoT Image Classification
Waqas, A., & Çöleri, S. (2025) · IEEE International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC) · doi:10.1109/pimrc62392.2025.11275242 · Cited by 4
“Furthermore, configurations that work well for one application may not generalize to others [11], [12], highlighting the need for application-specific bias in the optimization process.”
AI without borders: The rise of cross-disciplinary machine learning
Wibawa, A. P., Herdianto, R., Handayani, A. N., Utama, A. B. P., Aripriharta, Dwiyanto, F. A., & Dreżewski, R. (2026) · Telematics and Informatics Reports · doi:10.1016/j.teler.2026.100294 · Cited by 4
Automated Monitoring of Cultural Heritage Artifacts Using Semantic Segmentation
Ranieri, A., Palmieri, G., & Biasotti, S. M. (2026) · Lecture notes in mechanical engineering · doi:10.1007/978-3-032-14950-3_45 · Cited by 4
Shah, S. F. A., Khan, M. Q., Alsuwaylimi, A. A., & Alenezi, L. A. (2026) · IEEE Access · doi:10.1109/access.2026.3669588 · Cited by 4
“The paper in [25] Whilesome research papers provide general reviews of deep learning-based object detection models like in [28], and discuss their application in autonomous vehicles [21], they pay no special attention to the detection of abandoned objects.”
Automated and Simplified Waste Segregation System Using Convolutional Neural Networks and Python
Rajesh, G., Jayanthi, M., Kawale, S. S., Sainath, V., Revan, S. R., & Gurulakshmi, A. B. (2024) · International Conference on Computing, Communication and Networking Technologies (ICCCNT) · doi:10.1109/icccnt61001.2024.10724987 · Cited by 4
“Convolutional Neural Networks (CNNs) [3] have become a highly effective technology in recent years.”
BackgroundMpofu, K. T., & Mthunzi-Kufa, P. T. (2024) · MATEC Web of Conferences · doi:10.1051/matecconf/202440606001 · Cited by 4
Analisis dan Implementasi Metode Viola-Jones dan CNN pada Sistem Deteksi Kantuk Real-Time
Ritonga, A. S., & Muhandhis, I. (2024) · Jurnal Ilmiah IT CIDA · doi:10.55635/jic.v10i2.227 · Cited by 4
Abdullah, T., Kana Saputra, S., Syahputra, H., Indra, Z., & Kartika, D. (2025) · Journal of Artificial Intelligence and Engineering Applications (JAIEA) · doi:10.59934/jaiea.v4i2.719 · Cited by 4
Wang, W. P., Yin, T., & Pang, J. (2025) · Physics of Fluids · doi:10.1063/5.0257439 · Cited by 4
Pandey, A., Das, A. K., Wazid, M., Kaur, K., Park, Y., & Hassan, M. M. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3549720 · Cited by 4
“To evaluate the efficacy of the proposed authentication scheme, we implemented a convolutional neural network (CNN) [27] as part of a cognitive knowledge discovery process using the Python programming language and the Keras library within TensorFlow.”
OPTIMIZATION OF THE INCEPTIONV3 ARCHITECTURE FOR POTATO LEAF DISEASE CLASSIFICATION
Nur, K. N. A., Addyna, N. I., Windarto, A. P., Wanto, A., & Poningsih, P. (2025) · JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer) · doi:10.33480/jitk.v10i4.6554 · Cited by 4
AI-Based Analysis of Academic Culture in Christian Universities Using Hofstede VSM 2013
Faridah, I., Astrieta, D. A., Juliastuti, D., Anggraini, L., Pokkali, K. C., & Asri, A. (2025) · International Transactions on Artificial Intelligence (ITALIC) · doi:10.33050/italic.v3i2.733 · Cited by 4
Chen, Z., & Liu, T. (2025) · Remote Sensing · doi:10.3390/rs17152563 · Cited by 4
A Robust and Linguistically-Aware Hate Speech Detection System for Roman Urdu
Hashmi, E., Ahmad, H., Mazhar, M. T., Yayilgan, S. Y., Afzal, M., & Shaikh, S. (2025) · ACM Transactions on Asian and Low-Resource Language Information Processing · doi:10.1145/3768571 · Cited by 4
Deep Learning System for Speech Command Recognition
Vujičić, D., Damnjanović, Đ., Marković, D., & Stamenković, Z. (2025) · Electronics · doi:10.3390/electronics14193793 · Cited by 4
Das, D. H., Roy, S. D., Saha, P., & Bhowmik, M. K. (2024) · IEEE Transactions on AgriFood Electronics · doi:10.1109/tafe.2024.3365202 · Cited by 4
“Zeng et al. [60] proposed to use the classical architecture of LeNet [61] for bruise classification in pears in two major categories including bruise and unbruised pears.”
MethodPrianes, F., Fortuno, K. M. N., Onesa, R. O., Benosa, B., Palaoag, T. D., & Flores, N. (2024) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2024.0150352 · Cited by 4
“While computationally intensive, VGG architectures are known for their excellent performance in image classification tasks, demonstrating the importance of depth in CNNs [15].”
BackgroundTopological Properties on Neural Networks Using Graph Properties
Chandrashekar, K. K., Srirangan, J., & Dhivviyanandam, I. (2024) · Circuits Systems and Signal Processing · doi:10.1007/s00034-024-02898-6 · Cited by 4
“Krichen et al. [15] discussed the survey on CVNNs by providing the libraries and comparing their features and functionalities.”
Multi Path Real-time Semantic Segmentation Network in Road Scenarios
Pengfei, G., Tian, X., Cuihong, L., & Chenfei, Y. (2024) · International Journal of Intelligent Transportation Systems Research · doi:10.1007/s13177-024-00434-z · Cited by 4
Object-size-driven design of convolutional neural networks: virtual axle detection based on raw data
Riedel, H., Lorenzen, S. R., & Hübler, C. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.109803 · Cited by 4
“However, it is unclear whether spectograms still o ff er an advantage for deep learning models that have been optimised for raw signals.”
Suyahman, Sunardi, S., & Murinto (2024) · Scientific Journal of Informatics · doi:10.15294/sji.v11i4.13811 · Cited by 4
“Deep learning, particularly Convolutional Neural Networks (CNNs), has transformed image processing by automating feature extraction and hierarchical representation [4].”
Dlugas, H., & Kim, S. (2025) · Metabolites · doi:10.3390/metabo15030174 · Cited by 4
“Convolutional network-based machine learning Convolutional neural networks (CNNs), a variant of FNNs, particularly tend to perform well when observations are tensors of rank greater than one (e.g., image classification, image segmentation, computer vision) [16–20].”
Performance evaluation of reduced complexity deep neural networks
Agha, S., Nazir, S., Kaleem, M., Najeeb, F., & Talat, R. (2025) · PLoS ONE · doi:10.1371/journal.pone.0319859 · Cited by 4
“Batch normalization refers to the process of making the distribution of feature vectors, zero mean and unity variance [31–33].”
InfluentialHsiao, C. F., Feyrer, G., & Stein, A. (2025) · Smart Agricultural Technology · doi:10.1016/j.atech.2025.101023 · Cited by 4
Yogalakshmi, S., & Anitha, M. (2025) · International Conference on Inventive Computation Technologies (ICICT) · doi:10.1109/icict64420.2025.11004966 · Cited by 4
“Pooling layers reduce spatial dimensions to increase processing efficiency, while convolutional layers find patterns in specific locations [8].”
Classification of Alzheimer’s Disease by Magnetic Resonance Imaging with an Ensemble Approach
Silva, G. S., Cortes, O. A. C., & Jacob, A. F. L. (2025) · doi:10.5753/sbcas.2025.6919 · Cited by 4
Cordeiro, L. D. S., Nääs, I. D. A., & Okano, M. T. (2025) · AgriEngineering · doi:10.3390/agriengineering7080246 · Cited by 4
Beyond encryption: How deep learning can break microcontroller security through power analysis
Negabi, I., Asri, S. A. E., Adib, S. E., & Raissouni, N. (2025) · e-Prime - Advances in Electrical Engineering Electronics and Energy · doi:10.1016/j.prime.2025.100947 · Cited by 3
A study on the prediction of mountain slope displacement using a hybrid deep learning model
Ma, Y., Hu, X., Liu, Y., Shi, Y., Yu, Z., Wang, X., Hu, L., Liu, S., & Pang, D. (2025) · Discover Applied Sciences · doi:10.1007/s42452-025-07161-4 · Cited by 3
“When applied to small datasets, they are prone to overfitting—becoming too specialized to the training data and performing poorly on unseen samples [18, 19].”
Ma, Y., Ma, Y. C., Zheng, Q., & Chen, Q. (2025) · Water · doi:10.3390/w17192877 · Cited by 3
Campanile, L., de Biase, M. S., & Marulli, F. (2025) · Future Generation Computer Systems · doi:10.1016/j.future.2025.108217 · Cited by 3
Alkarkhi, M., Idris, N. H., & Rahman, M. Z. A. (2025) · International Journal of Remote Sensing · doi:10.1080/01431161.2025.2583603 · Cited by 3
“The Convolutional Neural Networks (CNNs) represent a category of deep learning models tailored to manage structured data formats, including images and time series (Crowley 2020; Krichen 2023; Rawat and Wang 2017).”
Alardhi, S. M., Breig, S. J. M., Salman, A. D., Rashed, I. A., Adnan, M., Kareem, F. A., & Mohammed, M. M. (2025) · Biomass and Bioenergy · doi:10.1016/j.biombioe.2025.108723 · Cited by 3
A Review on Deep Learning Frameworks for Dental Anomaly and Disease Classification
Ali, D. A., & Sadeeq, H. T. (2025) · Dasinya Journal for Engineering and Informatics · doi:10.65542/djei.v1i1.13 · Cited by 3
Ferroelectric memristors optimized in thickness for short-term memory-driven reservoir computing
Park, J., & Kim, S. (2026) · Journal of Materials Chemistry C · doi:10.1039/d5tc03983e · Cited by 3
Sustainable design of organic solar cells utilized machine and deep learning
Mohyeldien, O. M., El-Amary, N. H., & Bardawil, A. A. (2026) · Scientific Reports · doi:10.1038/s41598-026-35067-7 · Cited by 3
“…extraction; captures complex nonlinear relationships; strong generalization 42 High computational cost; lower interpretability and explainability 41 Random Forest (RF) Collection of many decision trees 43 Handles complex nonlinear relationships and feature interactions; manages unbalanced and…”
Adesina, A. F., Olorunfemi, B. O., Adeniji-Sofoluwe, A. T., Otuechere, C. A., Olopade, F., & Aribisala, B. S. (2026) · iLiver · doi:10.1016/j.iliver.2026.100225 · Cited by 3
Clinically Aligned Long-Context Transformers for Cross-Platform Mental Health Risk Detection
Tekale, A., & Masum, M. (2026) · Electronics · doi:10.3390/electronics15071403 · Cited by 3
Zhang, L., Yang, Y., He, Z., Li, G., Zhao, F., Hua, W., Xiao, G., & Zhang, J. (2026) · Remote Sensing · doi:10.3390/rs18071066 · Cited by 3
AI for pavement distress detection on lower-ranking roads: A bibliometric and systematic review
Zagvozda, M., Ljutić, K., Janić, V., & Barišić, I. (2026) · Advances in Civil and Architectural Engineering · doi:10.13167/2026.32.7 · Cited by 3
Formal Methods for Enhanced Natural Disaster Management
Krichen, M., & Alzahrani, M. Y. (2023) · IEEE/ACS International Conference on Computer Systems and Applications (AICCSA) · doi:10.1109/aiccsa59173.2023.10479311 · Cited by 3
“Using AI and ML, leaders can sift through the mountains of data collected for disaster management and gain useful insights to improve prevention, mitigation, and recovery activities [24]–[28].”
BackgroundSelf-citationEfficient traffic signal detection with tiny YOLOv4: enhancing road safety through computer vision
Santhiya, P., Jebadurai, I. J., Paulraj, G. J. L., Ebenezer, V., S., R. P. S. J., Keren, R., & Karan, K. (2024) · International Journal of Informatics and Communication Technology (IJ-ICT) · doi:10.11591/ijict.v13i2.pp285-296 · Cited by 3
“CNN is known for its identification and recognition of objects, which makes them more suitable for computer vision (CV) which plays a vital role in autonomous car and facial recognition systems [2].”
BackgroundMarroquin, L. A. S., & Cáceres, J. C. (2024) · Latin American Computer Conference (CLEI) · doi:10.1109/clei64178.2024.10700290 · Cited by 3
“The success of CNNs is due to the capture of spatial features and patterns in images by using their layers at different levels Krichen [5].”
BackgroundKolesnikov, A., Kosarev, N. S., Reznik, A. V., Немова, Н. А., Астапов, А. М., & Kropacheva, M. (2024) · Geodesy and Cartography · doi:10.22389/0016-7126-2024-1013-11-25-34 · Cited by 3
Saeed, H. S., & Fares, M. H. (2025) · Journal of Engineering and Sustainable Development · doi:10.31272/jeasd.2633 · Cited by 3
“It involves using filters, also known as kernels, that move across the input image to perform multiplication and addition operations at each element, creating feature maps [23].”
Mirsalehi, M., Fassbind, B., Streich, A. P., & Langenbucher, A. (2025) · PLoS ONE · doi:10.1371/journal.pone.0311036 · Cited by 3
Adaptive Graph Attention-Guided Parallel Sampling and Embedded Selection for Multi-Model Fitting
Yin, W., Lin, S., Suter, D., & Wang, H. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3755050 · Cited by 3
Advancements in hemotype identification: Fingerprint analysis for blood group determination
Vaidya, S. P., Tyagi, A., Ashok, S., Naga Satish, G., & Meenakshi, R. (2025) · Franklin Open · doi:10.1016/j.fraope.2025.100429 · Cited by 3
Zolfaghari, M., & Sajedi, H. (2025) · Soft Computing · doi:10.1007/s00500-025-10911-6 · Cited by 3
Wang, Z. (2024) · International Conference on Electrical Drives, Power Electronics & Engineering (EDPEE) · doi:10.1109/edpee61724.2024.00117 · Cited by 3
“Bengio et al. [2] proposed a multi-window BP neural language model in 2003, which effectively improved the representation quality of words by generating word vectors through training.”
BackgroundAI-Based Clustering of Numerical Flow Fields for Accelerating the Optimization of an Axial Turbine
Eyselein, S., Tismer, A., Raj, R., Rentschler, T., & Riedelbauch, S. (2025) · Energies · doi:10.3390/en18030677 · Cited by 3
Gbashi, S. M., Olatunji, O. O., Adedeji, P. A., & Madushele, N. (2025) · Journal of Reliable Intelligent Environments · doi:10.1007/s40860-025-00247-1 · Cited by 3
“Inspired by the human visual cortex, CNNs are a special class of deep learning models specifically designed for processing structured grid data, such as images [4].”
Das, T., Hasan, S. M. M., Efat, A. H., Faruk, M. F., Srizon, A. Y., Mamun, M. A., & Hossain, M. R. (2024) · International Conference on Electrical Engineering and Information Communication Technology · doi:10.1109/iceeict62016.2024.10534372 · Cited by 3
“They have demonstrated efficacy in tasks ranging from classification and prediction to signal denoising [11].”
BackgroundShaju, A. T., Jo, J. T., Abraham, E. S., Vishnuprasad, K., Deepa, V., & Mathew, J. (2024) · International Conference on Trends in Engineering Systems and Technologies (ICTEST) · doi:10.1109/ictest60614.2024.10576116 · Cited by 3
He, T., & Huang, W. (2024) · Applied Mathematics and Nonlinear Sciences · doi:10.2478/amns-2024-2435 · Cited by 3
Aftatah, M., & Zebbara, K. (2024) · International journal of Computer Networks & Communications · doi:10.5121/ijcnc.2024.16504 · Cited by 3
“Its main structure is illustrated in Figure 3 [20, 21, 22].”
BackgroundKorde, S. (2026) · International Journal of Clinical Research and Medical Sciences · doi:10.67231/qhxa9e37 · Cited by 3
Coulombe, V., Monfared, M. S., Aghel, K., Leboulleux, Q., Peralta, M. R., Blanchet, F. G., Gosselin, B. J., & Labonté, B. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.12.26.630112 · Cited by 3
Vyas, M., & Mehta, A. A. (2025) · medRxiv · doi:10.1101/2025.05.26.25328342 · Cited by 3
“The foundational layers are adept at identifying minute features, subsequently progressing to the more advanced layers, which discern larger features and intricate patterns [49,50,51,52].”
Ruijs, S., & Kosiakova, A. (2025) · Lund University Publications Student Papers (Lund University) · Cited by 3
Sharifi, M., Larraona, G. S., & Rivas, A. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.15536 · Cited by 3
“When trained on properly structured and normalized datasets, CNNs can act as fast, data-driven surrogates for computationally expensive simulations and as versatile tools for feature extraction, dimensionality reduction, and pattern recognition [9-12].”
Global Adoption of Artificial Intelligence in the Manufacturing Industries
Gatabazi, E., Mijwil, M. M., Abotaleb, M. S. A., & Kapaya, S. M. (2025) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3693-5231-1.ch015 · Cited by 2
Short-Term Load Forecasting Using Convolutional Neural Network for Chhattisgarh State
Shrivastava, S., Yadav, A., & Gupta, S. (2025) · Procedia Computer Science · doi:10.1016/j.procs.2025.04.585 · Cited by 2
Chen, J., Li, G., Wang, J., Sun, S., Sun, S., & Zhao, Y. (2025) · International Conference on Generative Artificial Intelligence and Information Security (GAIIS) · doi:10.1145/3728725.3728794 · Cited by 2
“Among these, the convolutional layer is paramount, giving the network its distinctive name [8].”
An adaptive deep learning approach for identification of crop-types from remote sensing images
Vatkar, S., & Kulkarni, S. (2025) · Evolving Systems · doi:10.1007/s12530-025-09702-z · Cited by 2
Chalmers, M., Gordon, K. C., McCane, B., & Fraser‐Miller, S. J. (2025) · Journal of Raman Spectroscopy · doi:10.1002/jrs.70002 · Cited by 2
Deep Learning and Transformers Accuracy in Rumor Detection on Social Media
Yu, L., Dai, J., Dai, J., & Wang, Y. (2025) · Annals of Emerging Technologies in Computing · doi:10.33166/aetic.2025.03.003 · Cited by 2
Zhang, J., Zhang, Q., Qiao, C., Mei, Z., Ren, K., & Chen, J. (2025) · Soft Computing · doi:10.1007/s00500-025-10895-3 · Cited by 2
“Their success is due to their ability to capture spatial features and patterns in images by using a hierarchical architecture of layers that perform convolution operations and extract features at different lev - els of abstraction (Krichen 2023).”
Rybak, A., Rybak, A., & Kolev, S. D. (2025) · Energies · doi:10.3390/en18205380 · Cited by 2
Relational Inductive Bias Behind Convolutional and Attention Neural Layers
Mijangos, V., Rodríguez‐Domínguez, U., & Arriola, V. E. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-09037-9_28 · Cited by 2
Hammoud, Y., Allali, Y., & Saadane, A. (2025) · Water Science · doi:10.1080/23570008.2025.2574171 · Cited by 2
“The CNN captures temporal dependencies by applying convolutional filters to the input sequence (Krichen, 2023), and the output is generated using the following formula (Equation 2): where W is the convolutional filter, x is the input sequence, b is the bias term, and ReLU is the activation function…”
The Evolution of Convolutional Neural Network Architectures: A Review
Mei, D., Gong, J., Qu, M., & Bian, S. (2025) · IEEE Access · doi:10.1109/access.2025.3631774 · Cited by 3
Multivariate input data for stock prediction using deep learning and hybrid models
Nag, N., Murugesan, R., & George, M. (2025) · Journal of Business Analytics · doi:10.1080/2573234x.2025.2587153 · Cited by 2
“As demonstrated by (Krichen, 2023) Convolutional Neural Networks (CNNs) employ convolutional filters to automatically extract hierarchical feature representations from raw input data, enabling the model to learn complex patterns without manual feature engineering, which enhances its generalization…”
Lian, J., Feng, W., Wang, Q., Dong, Y., Dauphin, G., & Bai, J. (2025) · Symmetry · doi:10.3390/sym17122172 · Cited by 2
3D Medical Image Reconstruction through Transformer-Based Neural Networks: A Comparative Study
Tan, W. L., & Menon, A. (2025) · Journal of Technology Informatics and Engineering · doi:10.51903/jtie.v4i3.453 · Cited by 2
TinyML-Powered Handwritten Digit Recognition Device for the Visually Impaired
Ogundipe, A., Oloye, T. I., & Zubair, A. R. (2026) · International Journal of Advanced Networking and Applications · doi:10.35444/ijana.2025.17406 · Cited by 2
Sáez-Pardo, F., Giner-Sanz, J. J., & Pérez-Herranz, V. (2026) · Journal of Electroanalytical Chemistry · doi:10.1016/j.jelechem.2026.119893 · Cited by 2
Comparative Analysis of Hybrid CNN-ViT and CNN for Brain Tumor Classification
Fauzi, A., Fuadi, A. L., & Yunial, A. H. (2026) · JISKA (Jurnal Informatika Sunan Kalijaga) · doi:10.14421/jiska.5860 · Cited by 2
“A systematic data augmentation method was exclusively applied to the training images to boost the models' generalization capabilities and extend the distributional representation of the training data (Krichen, 2023).”
Image-Based Hybrid Neural Network Model for Naval Ship Wave Resistance Prediction
Hassan, H. M., & Saad-Eldeen, S. (2026) · Journal of Marine Science and Engineering · doi:10.3390/jmse14030309 · Cited by 2
“Convolutional Neural Networks ( CNNs ) are a class of deep learning models designed to automatically extract spatial features from grid-structured data such as images [31,32].”
Benchmarking Lightweight Convolution Neural Networks for Children’s Arabic Handwriting
Ladrham, K., Gueddah, H., & Hssain, B. O. (2026) · Journal of Innovative Image Processing · doi:10.36548/jiip.2026.1.012 · Cited by 2
Zolfaghari, M., Abadeh, M. S., & Sajedi, H. (2026) · PLoS ONE · doi:10.1371/journal.pone.0336770 · Cited by 2
A Multi-Model Hybrid Framework for Twitter Spam Detection using LSTM, CNN and GAN
Pereira, L., & Nagasundaram, S. (2026) · International Conference on Electronics and Renewable Systems (ICEARS) · doi:10.1109/icears67481.2026.11416630 · Cited by 2
“We have proposed a system for detecting spam created in this research by integrating three DL models, which are LSTM [24], CNN [25] and GAN [26, 27].”
Jabali, E. H., Almomani, O., Qatawneh, L., Badwan, S. A., Almomani, Y., Al-Soreeky, M. S., Ibrahim, A., & Khalil, N. (2026) · Journal of Imaging · doi:10.3390/jimaging12030121 · Cited by 2
“One subgroup of deep learning algorithms, the convolutional neural networks (CNNs) [12,13], which are trained to extract hierarchies of spatial gradients of visual features directly from raw image data, has demonstrated outstanding ability to be successfully used in medical imaging, such as cancer…”
Refining emotion recognition: Attention-enhanced deep neural networks for facial analysis
Hallur, S., & Gavade, A. B. (2026) · Franklin Open · doi:10.1016/j.fraope.2026.100603 · Cited by 2
Evaluating the Efficacy of Convolutional Neural Networks: Disease Detection in Crops
Mensah, S. A., Amoatey, P. K., Ofori, P. A., Owusu-Nketia, S., Sabi, E. B., Dwomoh, F. A., Simpson, A. R., & Asenso, E. (2026) · Advances in Agriculture · doi:10.1155/aia/3578856 · Cited by 2
A review of machine vision and deep learning applications in grain quality inspection
Wang, B. (2026) · Emirates Journal of Food and Agriculture · doi:10.3897/ejfa.2026.175268 · Cited by 2
LCVision: deep learning model for recognition of nematic and smectic phases in liquid crystals
Agarwal, N., Gupta, D., Thalakodan, I. B. H., & Bhattacharjee, A. (2026) · The European Physical Journal Special Topics · doi:10.1140/epjs/s11734-026-02507-4 · Cited by 2
Kashavar, M. M., Shahbazi, Y., Amirkhiz, H. S., & Pedrammehr, S. (2026) · Discover Civil Engineering · doi:10.1007/s44290-026-00582-z · Cited by 2
“This emphasis on noise robustness aligns with Liang et al. [18], who proposed a CNN-RNN stacking ensemble to denoise vibration signals, underscoring the critical role of preprocessing in improving input quality for downstream SHM tasks.”
Convolutional Neural Network for COVID-19 Detection Using InceptionV3 Transfer Learning
Pratama, D. R. A. N., & Azhar, Y. (2025) · Jurnal Teknik Informatika (Jutif) · doi:10.52436/1.jutif.2025.6.2.4094 · Cited by 2
A Neural Network Compiler for Efficient Data Storage Optimization in ReRAM-Based DNN Accelerators
Kao, H.-Y., Su, L.-Y., Huang, S.-H., & Cheng, W. (2025) · Electronics · doi:10.3390/electronics14122352 · Cited by 2
Mohammadi, H., Thirunarayan, K., & Chen, L. (2023) · Sensors · doi:10.3390/s23249893 · Cited by 2
“Deep Neural Network (DNN) models, a subset of ML models, have particularly flour-ished in intelligent sensor applications, demonstrating remarkable success in computer vision [10,11], speech recognition [12], natural language processing [13], and numerous other fields [14–16].”
BackgroundMulti‐view synergistic enhanced fault recording data for transmission line fault classification
Jia, M., Huang, X., Han, F., Yan, D., Wang, W., Zhu, G., Zhang, L., Pan, C., Ma, H., & Wei, J. (2024) · IET Communications · doi:10.1049/cmu2.12784 · Cited by 2
Implementation of Intelligent Elderly Care System Based on Cloud Platform and NNB Algorithm
Huang, X., & Palaoag, T. D. (2024) · IEEE International Conference on Control, Electronics and Computer Technology (ICCECT) · doi:10.1109/iccect60629.2024.10546115 · Cited by 2
“BP neural network [8] is a multi-layer feedforward neural network whose learning algorithm adjusts each weight parameter in the network based on the error backpropagation mechanism.”
MethodGlaucoma Detection through Synergistic Combination of Image Processing and Deep CNN using MATLAB
Subbarayudu, B., Yadalam, H., Seepiri, J., & Bhogathi, J. (2024) · International Conference for Emerging Technology (INCET) · doi:10.1109/incet61516.2024.10593177 · Cited by 2
“CNNs have been applied to achieve cutting-edge performance not only in finding complex patterns inside images, which are important to detect the subtle signs of pre-glaucoma, but also in segmentation, a classical task of computer vision [19].”
BackgroundMethodVery Short-Term Prosumer Electric Load Forecasting Using Deep Learning-Based Techniques
Aydın, B., Zor, K., & Dişken, G. (2024) · International Youth Conference on Energy · doi:10.1109/iyce60333.2024.10634913 · Cited by 2
“Typically, the convolutional operation is expressed as follows: where x and w are two functions that can be either discrete or continuous, and k is the output signal position [17].”
BackgroundTeknologi Computer Vision untuk melakukan Deteksi dan Penentuan Kualitas Bibit Ayam Day Old Chicks
Syaddam, S., Soeksin, S. D., & Nizar, R. (2024) · Jurnal Informatika Jurnal Pengembangan IT · doi:10.30591/jpit.v9i3.7923 · Cited by 2
State Prediction Model of Steel Structure Based on VMD-CNN Method
Li, X., Xue, T., Suo, S., Li, W., Bai, Y., Wang, P., & Sun, L. (2024) · International Journal of Structural Stability and Dynamics · doi:10.1142/s0219455426501385 · Cited by 2
Federated Learning for COVID-19 Detection: Optimized Ensemble Weighting and Knowledge Distillation
Annan, R., & Qingge, L. (2024) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm62325.2024.10822329 · Cited by 2
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.