The DOI matches its Crossref record, with a small difference in title or year; 31 of the 31 references it cites were found in a registry or an index; 2 of the 14 sources its claims cite were checked for support.
ImageNet classification with deep convolutional neural networks
Open accessAbstract
We trained a large, deep convolutional neural network to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes. On the test data, we achieved top-1 and top-5 error rates of 37.5% and 17.0%, respectively, which is considerably better than the previous state-of-the-art. The neural network, which has 60 million parameters and 650,000 neurons, consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully connected layers with a final 1000-way softmax. To make training faster, we used non-saturating neurons and a very efficient GPU implementation of the convolution operation. To reduce overfitting in the fully connected layers we employed a recently developed regularization method called "dropout" that proved to be very effective. We also entered a variant of this model in the ILSVRC-2012 competition and achieved a winning top-5 test error rate of 15.3%, compared to 26.2% achieved by the second-best entry.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
42 Own result · 21 Own interpretation · 7 No basis given · 4 No full text of the sources · 3 Sources not found · 2 Supported · 2 Not checked yet · 1 Own method
Every source the paper cites for this claim was checked and supports it.
In the paper
“This technique reduces complex co adaptations of neurons, since a neuron cannot rely on the presence of particular other neurons.”
§ ImageNet Classification with Deep Convolutional Neural Networks > 5.2. Dropout
What the sources say
- Supportedcites [12] 12. Hinton, G., Srivastava, N., Krizhevsky, A., Sutskever, I., Salakhutdinov, R. Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv:1207.0580 (2012). source
The paper states on p. 1 that dropout prevents complex co-adaptations by randomly omitting hidden units, so a hidden unit cannot rely on other hidden units being present. This directly supports the citing sentence. (LLM, conf=0.95)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“There is, however, a very efficient version of model combination that only costs about a factor of two during training.”
§ ImageNet Classification with Deep Convolutional Neural Networks > 5.2. Dropout
What the sources say
- Supportedcites [12] 12. Hinton, G., Srivastava, N., Krizhevsky, A., Sutskever, I., Salakhutdinov, R. Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv:1207.0580 (2012). source
The paper describes dropout as an efficient way to combine many neural-network models (p. 1). In F.6 Training (p. 17), it reports that ImageNet training took roughly four days with dropout versus two days without it, supporting the approximate factor-of-two training cost. (LLM, conf=0.88)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“This scheme reduces our top-1 and top-5 error rates by 1.7% and 1.2%, respectively, as compared with a net with half as many kernels in each convolutional layer trained on one GPU.”
§ ImageNet Classification with Deep Convolutional Neural Networks > 4.2. Training on multiple GPUs
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The size of our network made overfitting a significant problem, even with 1.2 million labeled training examples”
§ ImageNet Classification with Deep Convolutional Neural Networks > 2. INTRODUCTION
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“So these data augmentation schemes are, in effect, computationally free.”
§ ImageNet Classification with Deep Convolutional Neural Networks > 5.1. Data augmentation
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- It may state two separate claims as one. 18
- Probably not a substantial claim. 26
- The quote only partly states this claim. 2
Create a free account to see these claims.
Create a free account to see these assumptions.
34 more claims
Create a free account to see all 82 claims and to verify the 3 references still open.
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?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“In the field of DL, the CNN is the most famous and commonly employed algorithm [30, 71–75].”
From Review of deep learning: concepts, CNN architectures, challenges, applications, future directions (2021) · cites this paper as [30]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Convolutional neural networks (CNNs), built for spatial data, have demonstrated performance comparable to that of specialists in cancer detection and tumor segmentation [15,16,17,18,19,20].”
From Artificial Intelligence in Clinical Oncology: From Productivity Enhancement to Creative Discovery (2025) · cites this paper as [16]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Deep CNN architectures with 8, even 22 layers [4], [33], can be useful even for CADe problems where the available training datasets are limited.”
From Deep convolutional neural networks for computer-aided detection: cnn architectures, dataset characteristics and transfer learning (2016) · cites this paper as [4]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Fully convolutional neural networks (fCNNs) have provided state-of-the-art performance for object classification and image segmentation (1).”
From Fully automated, real-time 3D ultrasound segmentation to estimate first trimester placental volume using deep learning (2018) · cites this paper as [1]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The first wave saw the emergence of deep learning as the dominant paradigm for analyzing high-dimensional biological data.”
From The next paradigm in bioinformatics: a review of multi-agent systems and foundational models for end-to-end scientific discovery (2026) · cites this paper as [1]
Experimental — accuracy not yet measured
19 more claims about this paper
Create a free account to see every claim other papers make about this one.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ ImageNet Classification with Deep Convolutional Neural Networks > 2. INTRODUCTION
“we found that removing any convolutional layer (each of which contains no more than 1% of the model's parameters) resulted in inferior performance.”
§ ImageNet Classification with Deep Convolutional Neural Networks > 4.5. Overall architecture
“The third convolutional layer has 384 kernels of size 3 × 3 × 256”
Citations
Cites
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
Learning Multiple Layers of Features from Tiny Images
Krizhevsky, A. (2024) · doi:10.57702/zp44cu3g · Cited by 23,884
Self-citationLearning Internal Representations by Error Propagation
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1985) · doi:10.21236/ada164453 · Cited by 16,501
Self-citation(2010) · International Conference on Machine Learning · Cited by 13,995
Self-citationImproving neural networks by preventing co-adaptation of feature detectors
Hinton, G. E., Srivastava, N., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. R. (2012) · arXiv · doi:10.48550/arxiv.1207.0580 · Cited by 6,382
Self-citationFukushima, K. (1980) · Biological Cybernetics · doi:10.1007/bf00344251 · Cited by 5,759
LabelMe: A Database and Web-Based Tool for Image Annotation
Russell, B. C., Torralba, A., Murphy, K. P., & Freeman, W. T. (2008) · International Journal of Computer Vision · doi:10.1007/s11263-007-0090-8 · Cited by 4,210
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1512.03385 · Cited by 4,196
Research works printed but not linked: 13
- Berg A., 2010, Large scale visual recognition challenge
- Deng J., 2009, CVPR09
- Krizhevsky A., 2009, Department of Computer Science
- Krizhevsky A., 2010, Convolutional deep belief networks on cifar-10. Unpublished manuscript
- Krizhevsky A., 2011, ESANN
- LeCun Y., 1990, Advances in Neural Information Processing Systems
- LeCun Y., 1985, Une procedure d'apprentissage pour reseau a seuil asymmetrique (a learning scheme for asymmetric threshold networks)
- 10.5555/1896300.1896315 · DOI
- Mensink T., 2012, Italy
- 10.5555/3104322.3104425 · DOI
- Rumelhart D.E., 1985, DTIC Document
- 10.5555/938980.939477 · DOI
- Werbos P., 1974, Beyond regression: New tools for prediction and analysis in the behavioral sciences
Cited by
Items 58,401–58,500 of 108,438
Yadav, V. K., & Singhai, J. (2025) · IETE Technical Review · doi:10.1080/02564602.2025.2501936 · Cited by 8
Seo, I.-J., Lee, Y.-H., & Jang, B. (2025) · PLoS ONE · doi:10.1371/journal.pone.0324621 · Cited by 8
Implications of Artificial Intelligence for Assessing the Built Environment
Moradi, F., & Biloria, N. M. (2025) · Journal of Urban Technology · doi:10.1080/10630732.2025.2468142 · Cited by 9
Sun, Z., Wang, H., Xie, Q., et al. (2025) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2025.3560082 · Cited by 7
Akingbola, A., Christopher, A. A., Ojo, O., Jessica, O. U., Alao, U. H., Owolabi, A. O., & Chuku, J. (2025) · Global Health · doi:10.1155/ghe3/8898076 · Cited by 11
Image captioning using bidirectional LSTM neural network
Hoseini, F., & Notash, A. Y. (2025) · Discover Artificial Intelligence · doi:10.1007/s44163-025-00315-8 · Cited by 7
Das, M., Ferreira, G., & Chen, C. J. (2025) · Smart Agricultural Technology · doi:10.1016/j.atech.2025.101054 · Cited by 7
Multi-task multi-modal graph neural network for recommender system
Jiao, S., Zhang, Y., & Hara, T. (2025) · Knowledge and Information Systems · doi:10.1007/s10115-025-02456-9 · Cited by 9
Robust Face Recognition Using Deep Learning and Ensemble Classification
Chitrapu, P., Morampudi, M. K., & Kalluri, H. K. (2025) · IEEE Access · doi:10.1109/access.2025.3575192 · Cited by 13
Dalhat, M. A., & Osman, S. A. (2025) · Artificial Intelligence in Geosciences · doi:10.1016/j.aiig.2025.100127 · Cited by 6
Chen, J., Yao, J., Chen, W., Zhang, F., Wang, H., Xu, X., Ge, H., Zhou, H., Cen, J., Li, D., et al. (2025) · EBioMedicine · doi:10.1016/j.ebiom.2025.105755 · Cited by 7
Pan, J., Li, F. W. B., Yang, B., & Nan, F. (2025) · Computer Animation and Virtual Worlds · doi:10.1002/cav.70053 · Cited by 11
Ali, S. A., Arain, K. R., Mushtaq, N.-U.-A., & Rehman, O. U. (2025) · VFAST Transactions on Software Engineering · doi:10.21015/vtse.v13i2.2082 · Cited by 10
Gong, Y., Jiang, Y., Cheng, C., & Wang, S. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3577846 · Cited by 8
Banyong, C., Hantanong, N., Nanthawong, S., Se, C., Wisutwattanasak, P., Champahom, T., Ratanavaraha, V., & Jomnonkwao, S. (2025) · Big Data and Cognitive Computing · doi:10.3390/bdcc9060155 · Cited by 7
Tiny-MobileNet-SE: A Hybrid Lightweight CNN Architecture for Resource-Constrained IoT Devices
Nyakuri, J. P., Nkundineza, C., Gatera, O., & Nkurikiyeyezu, K. N. (2025) · IEEE Access · doi:10.1109/access.2025.3582055 · Cited by 10
Abe, H., & Nyathi, M. (2025) · JMIR Bioinformatics and Biotechnology · doi:10.2196/68848 · Cited by 15
Zhang, J., & Zhang, H. (2025) · Mathematics · doi:10.3390/math13132087 · Cited by 8
Yan, Q., Pei, Y., Xue, L., Sun, H., Wang, R., & Ran, X. (2025) · Ore Geology Reviews · doi:10.1016/j.oregeorev.2025.106758 · Cited by 7
A Survey on the Scheduling of DL and LLM Training Jobs in GPU Clusters
Fu, T., Yang, Z., Ye, Z., Ma, C., Han, Y., Luo, Y., Wang, X., & Wang, Z. (2025) · Chinese Journal of Electronics · doi:10.23919/cje.2024.00.070 · Cited by 10
Keshmiri, M., Dehgahi, S., Mohiuddin, A., & Qureshi, A. J. (2025) · Scientific Reports · doi:10.1038/s41598-025-04125-x · Cited by 8
“Typically, CNNs consist of convolutional layers, activation layers, pooling layers, and fully-connected layers 58 .”
Artificial intelligence in ophthalmology: a bibliometric analysis of the 5-year trends in literature
Peng, B., Mu, J., Xu, F., Guo, W., Sun, C., & Fan, W. (2025) · Frontiers in Medicine · doi:10.3389/fmed.2025.1580583 · Cited by 10
Generative Artificial Intelligence in Prostate Cancer Imaging
Haque, F., Simon, B., Özyörük, K. B., Harmon, S. A., & Türkbey, B. (2025) · Balkan Medical Journal · doi:10.4274/balkanmedj.galenos.2025.2025-4-69 · Cited by 7
“Authors also trained a lesion detection AI model using AlexNet 43 which achieved an accuracy of 76.2% while training on both real and synthetic sequences in comparison to 70.4% for models trained on the real sequences.”
InfluentialYang, H., He, H., Li, Y., & Cao, F. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.128802 · Cited by 7
Kaur, K., Kaur, H., Singh, M. L., et al. (2025) · Potato Research · doi:10.1007/s11540-025-09891-9 · Cited by 7
The Lightweight Method of Ground Penetrating Radar (GPR) Hidden Defect Detection Based on SESM-YOLO
Yan, Y. J., Jiao, G., Cui, M., & Ni, L. (2025) · Buildings · doi:10.3390/buildings15132345 · Cited by 9
Wang, H., Xiang, Y., Liu, Z., Yin, W., Li, B., Qian, L., Wang, X., & Lou, C. (2025) · Nucleic Acids Research · doi:10.1093/nar/gkaf611 · Cited by 8
“CNNs [ 33 ], a type of DL models, have emerged as promising tools for predicting transcriptional regulation from regulatory sequences in recent studies.”
Römer, P., Ponciano, J.-J., Kloster, K., et al. (2025) · JMIR Medical Informatics · doi:10.2196/76148 · Cited by 7
A lightweight CNN-LSTM hybrid model for land cover classification in satellite imagery
Hasan, N., & Islam, M. S. (2025) · Geocarto International · doi:10.1080/10106049.2025.2521828 · Cited by 8
“…(DBN) (Hinton et al. 2006), Stacked Auto-Encoders (SAE) ( € Ozt € urk 2020), and deep Convolutional Neural Networks (CNNs) (Szegedy et al. 2015; Krizhevsky et al. 2017) represent the most effective models for satellite image segmentation, object detection (Chen et al. 2014), and…”
Performance of xLSTM for Semantic Segmentation of Remotely Sensed Images
Zhu, Q., Cai, Y., & Fan, L. (2024) · International Conference on Sensors, Signal and Image Processing (SSIP) · doi:10.1145/3725949.3725967 · Cited by 13
Perceptual Carlini-Wagner Attack: A Robust and Imperceptible Adversarial Attack Using LPIPS
Fan, L., Khairuddin, A. S. M., Liu, H. L., et al. (2025) · IEEE Access · doi:10.1109/access.2025.3588113 · Cited by 7
Singh, V., Jyoti, A., Jain, P., Saxena, J., Khanra, A., Vasistha, S., Das, P., Shyam, L., Khan, S. A., Parikh, S. M., et al. (2025) · ACS Chemical Health & Safety · doi:10.1021/acs.chas.5c00045 · Cited by 7
Intelligent prediction of TBM thrust force based on passive source seismic vibration signals
Wang, X., Zhou, H., Lu, M., Wei, X., & Lu, S. (2025) · Automation in Construction · doi:10.1016/j.autcon.2025.106395 · Cited by 8
Dubey, P., Dubey, P., Dubey, P., et al. (2025) · Machine Learning and Knowledge Extraction · doi:10.3390/make7030067 · Cited by 7
An attention-enhanced ResNet model for classification of TBM rock chips
Li, F., Liu, Q., Pan, Y., et al. (2025) · Tunnelling and Underground Space Technology · doi:10.1016/j.tust.2025.106916 · Cited by 7
Integrating radius margin constraints and class variance for improved CNN-based image recognition
Jiang, Q., Xiao, Y. X., Zhou, G., et al. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.114188 · Cited by 7
ResQ: A hybrid classical-quantum model for efficient breast cancer image classification
Guha, D., Kuiry, S., Mitra, S., Bhattacharyya, S., & Das, N. (2025) · Applied Soft Computing · doi:10.1016/j.asoc.2025.113631 · Cited by 9
A Survey of Deep Learning Methods and Tools for Protein Binding Site Prediction
Rohulia, A., Wang, Y., & Cheng, J. (2025) · Methods in molecular biology · doi:10.1007/978-1-0716-4662-5_5 · Cited by 6
Are deep learning models robust to partial object occlusion in visual recognition tasks?
Kassaw, K., Luzi, F., Collins, L. M., & Malof, J. M. (2025) · Pattern Recognition · doi:10.1016/j.patcog.2025.112215 · Cited by 11
Jeon, J., Rabault, J., Vasanth, J., Alcántara-Ávila, F., Baral, S., & Vinuesa, R. (2025) · Physics of Fluids · doi:10.1063/5.0276738 · Cited by 14
A Survey of Event Causality Identification: Taxonomy, Challenges, Assessment, and Prospects
Cheng, Q., Zeng, Z., Hu, X., Si, Y., & Liu, Z. (2025) · ACM Computing Surveys · doi:10.1145/3756009 · Cited by 19
Saket, O., Aicha, A. B., & Fathallah, H. (2025) · Applied Intelligence · doi:10.1007/s10489-025-06797-4 · Cited by 9
A Contrastive Representation Learning Method for Event Classification in Φ-OTDR Systems
Zhang, T., Peng, X., Liu, Y., et al. (2025) · Sensors · doi:10.3390/s25154744 · Cited by 7
Anjum, S., & Nnaji, C. A. (2025) · Automation in Construction · doi:10.1016/j.autcon.2025.106447 · Cited by 7
Automatic detection of foreign object intrusion along railway tracks based on MACENet
Chen, X., Tian, Y., Li, M., Lv, B., Zhang, S., Qu, Z., Wu, J., & Cheng, S. (2025) · PLoS ONE · doi:10.1371/journal.pone.0329303 · Cited by 7
“AlexNet’s [17] triumph in the ImageNet competition was a landmark achievement for deep convolutional neural networks, heralding deep learning’s breakthrough in image recognition [18].”
Akan, T., Alp, S., Bhuiyan, M. S., et al. (2025) · Intelligent Medicine · doi:10.1016/j.imed.2025.07.001 · Cited by 7
SAR remote sensing for monitoring harmful algal blooms using deep learning models
Phetanan, K., Kwon, D. H., Lee, J., Jeong, H., Nam, G., Hwang, E., Pyo, J., & Cho, K. H. (2025) · GIScience & Remote Sensing · doi:10.1080/15481603.2025.2524202 · Cited by 12
Deep Learning in Gravity Research: A Review
Meng, Q., Guo, L., Zhang, S., Lou, H., & Li, R. (2025) · Journal of Earth Science · doi:10.1007/s12583-023-1926-x · Cited by 11
“Based on these frameworks, extensions such as AlexNet (Krizhevsky et al., 2017), ResNet (He et al., 2016), GoogLeNet (Szegedy et al., 2015), GRU (Cho et al., 2014), and VGG (Simonyan and Zisserman, 2014) have been developed, significantly improving the level of audio, video and image recognition…”
Khan, U., Khan, S. F., Khalil, I. U., & Ahsan, M. (2025) · Measurement · doi:10.1016/j.measurement.2025.118537 · Cited by 11
Machine learning-optimized stochastic Voronoi lattices for enhanced mechanical performance
Thompson, M., Sarvestani, H. Y., Kashani, A. S., Kiyani, E., Filippi, E., van Egmond, D. A., Rahmat, M., Ashrafi, B., & Karttunen, M. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.111937 · Cited by 7
Yi, J., Lopez, G., Hadir, S., Weyler, J., Klingbeil, L., Deichmann, M., Gall, J., & Seidel, S. J. (2025) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2025.110865 · Cited by 8
Khan, A., Ullah, H., & Munir, A. (2025) · AI · doi:10.3390/ai6090197 · Cited by 8
Mahmood, T., Saba, T., Rehman, A. U., & Alamri, F. S. (2025) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2025.102621 · Cited by 10
Synergizing microfluidics and machine learning for next generation intelligent Lab-on-a-Chip devices
Das, S. (2025) · Microchemical Journal · doi:10.1016/j.microc.2025.114862 · Cited by 11
A comprehensive review of facial beauty prediction using deep learning techniques
Boukhari, D. E., Dornaika, F., Chemsa, A., & Ahmed, A. T. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.112009 · Cited by 9
A compressed hierarchy for visual form processing in the tree shrew
Lanfranchi, F. F., Wekselblatt, J. B., Wagenaar, D. A., & Tsao, D. Y. (2025) · Nature · doi:10.1038/s41586-025-09441-w · Cited by 9
“Such category-selective regions can be explained by a normative framework in which IT cortex encodes a general object space—a representational space defined by the first two principal components of the AlexNet FC6 features 8,45 .”
InfluentialDefect detection in 3D printing: a review of image processing and machine vision techniques
Armin, E., Ebrahimian, S., Sanjari, M., Saidi, P., & Pourreza, H. R. (2025) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-025-16382-1 · Cited by 10
“This paradigm shift has led to significant advancements in fields like image recognition, speech processing, and defect detection in manufacturing [32].”
Huijben, E. M. C., Amirrajab, S., & Pluim, J. P. W. (2025) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2025.109045 · Cited by 7
Climate impacts and future trends of hailstorms in China based on millennial records
Zhang, Q., Li, R., Li, W., Li, X., Ng, C., Zhang, S., & Zhao, C. (2025) · Nature Communications · doi:10.1038/s41467-025-63028-7 · Cited by 10
Flow temperature field reconstruction based on physics-informed neural network
Yang, Y., Xu, Y., Wang, H., et al. (2025) · Physics of Fluids · doi:10.1063/5.0284621 · Cited by 7
Detection and classification of power quality disturbances: Vision transformers vs. CNN
Anwar, M. H., Baig, M. M. A., Shaikh, A. J., & Abro, A. G. (2025) · AIMS energy · doi:10.3934/energy.2025039 · Cited by 9
Sequential recommender systems: A methodological taxonomy and research frontiers
Zhou, Y., Ma, G., Wen, X., Yang, X.-H., & Zhang, Y. (2025) · Computer Science Review · doi:10.1016/j.cosrev.2025.100818 · Cited by 11
MSCA-Net: Multi-scale context aggregation network for infrared small target detection
Lu, X., Yue, T., Cai, J., et al. (2025) · Optics & Laser Technology · doi:10.1016/j.optlastec.2025.113894 · Cited by 7
Fan, Y., Ji, Z., Sun, C., et al. (2025) · Applied Food Research · doi:10.1016/j.afres.2025.101374 · Cited by 7
Wu, H., Li, H., Fang, X., Tang, M., Yu, H., Yu, B., Li, M., Jing, Z., Meng, Y., Chen, W., et al. (2025) · Speech Communication · doi:10.1016/j.specom.2025.103313 · Cited by 8
Crack Segmentation Using U-Net and Transformer Combined Model
Noh, J.-H., Jang, J., Jo, J., et al. (2025) · Applied Sciences · doi:10.3390/app151910737 · Cited by 7
Zhu, Q., Li, K., Zhang, G., et al. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3617006 · Cited by 7
Real-time gas dispersion model prediction on offshore platforms based on CNN_Transformer model
Li, H., Lin, H., Zhu, Z., et al. (2025) · Process Safety and Environmental Protection · doi:10.1016/j.psep.2025.107983 · Cited by 7
Adam, A., Stallard, S., Fang, H., & Li, X. (2025) · Transport in Porous Media · doi:10.1007/s11242-025-02239-4 · Cited by 7
“A previous study (Adam et al. 2024) provides evidence that varying the number of convolutional layers from the original architecture (Simonyan and Zisserman 2015; Krizhevsky et al. 2017) yields no benefit.”
InfluentialDeep Learning-Based Fish Health Monitoring and Diagnosis: A Review
Khriji, L., Kouadri, A., & Mansouri, M. M. (2025) · IEEE Access · doi:10.1109/access.2025.3621487 · Cited by 7
Dai, J., Wen, Z., Ali, M. K., Huang, J., Liu, S., Zhao, J., Pinheiro, F., Yang, C., Wang, B., Ye, L., et al. (2025) · GigaScience · doi:10.1093/gigascience/giaf129 · Cited by 6
“…of the proposed method, we further applied the SeedGerm-VIG pipeline to test other cereal crops such as barley and rice through transfer learning [ 50 ], so that the pretrained DL models could be quickly fine-tuned with significantly reduced epochs and smaller training sets, indicating the…”
LL-YOLO: A lightweight pavement disease detection algorithm in low-light environments
Jia, Y., Yang, C., & Gao, Y. (2025) · Measurement · doi:10.1016/j.measurement.2025.119494 · Cited by 10
Intelligent Flexible Position Antenna Systems for Networking: A Survey
Yu, X., Wang, J., Hu, R. Q., Kim, D. I., Al‐Dhahir, N., Wymeersch, H., & Zhao, N. (2025) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2025.3626312 · Cited by 11
Adachi, Y., Ueda, K., Otaki, Y., Hashimoto, M., Sowa, H., Kawahara, T., Numata, G., Nakamura, S., Hinata, M., Uehara, M., et al. (2025) · Radiology Cardiothoracic Imaging · doi:10.1148/ryct.240521 · Cited by 7
Wang, J., Fang, X., Song, Y., & He, D. (2025) · Tunnelling and Underground Space Technology · doi:10.1016/j.tust.2025.107292 · Cited by 7
Frontiers and advances of deep learning-based fruit and vegetable image analysis
Ma, J., Wan, Y., Min, W., et al. (2025) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2025.111256 · Cited by 7
Niu, Y., Zheng, Y.-L., Shi, S.-J., et al. (2025) · Engineering applications of artificial intelligence · doi:10.1016/j.engappai.2025.112754 · Cited by 9
Peng, C., Zheng, J., Chen, T., et al. (2025) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2025.113763 · Cited by 7
RLBindDeep: A ResNet-LSTM based novel framework for protein–ligand binding affinity prediction
Lodh, E., Majumder, S., Chowdhury, T., & De, M. (2026) · Journal of Molecular Graphics and Modelling · doi:10.1016/j.jmgm.2026.109282 · Cited by 8
Abbas, M. J., Khan, M. A., Ahmed, W., Hamza, A., Hadj-Alouane, N. B., Alsenan, S. A., Alouane, M. T.-H., & Nam, Y. (2026) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2026.3651659 · Cited by 8
Demand Prediction of New Electric Vehicle Charging Stations: A Deep Learning Approach
Zheng, J., Zhang, J., Jia, R., Song, P., & Zhao, S. (2026) · Energies · doi:10.3390/en19020378 · Cited by 8
Avakian, A., & Barfoot, G. (2026) · BMC Artificial Intelligence · doi:10.1186/s44398-025-00020-7 · Cited by 12
“These models are used for classification, detection, and segmentation tasks across modalities including CT, MRI, and mammography [1, 2, 5, 6] applications may lack the visibility of diagnostic break-throughs, but their cumulative impact is substantial.”
Deep learning characterization of stress-state-dependent anisotropic ductile damage
Wei, Z., Mo, Y., Zhou, S., Gerke, S., Münstermann, S., & Brünig, M. (2026) · International Journal of Mechanical Sciences · doi:10.1016/j.ijmecsci.2026.111424 · Cited by 8
Ghimire, S., Lamsal, R., Sankuratri, A., Lakkarsu, P., & Vutla, S. (2026) · The Plant Pathology Journal · doi:10.5423/ppj.rw.01.2026.0004 · Cited by 14
“AlexNet (Krizhevsky et al., 2012) introduced key innovations such as ReLU activations, dropout regularization, and GPU-based training, achieving a top 5 error rate of 15.3% on ImageNet.”
InfluentialLan, G., Xiao, S., Wen, J.-B., Yang, J.-C., Lu, W., Li, B.-H., Meng, Q.-G., & Gao, X.-B. (2026) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2026.3678220 · Cited by 14
Mahmud, M. I., & Banerjee, T. (2026) · Briefings in Bioinformatics · doi:10.1093/bib/bbag229 · Cited by 12
“The success of AlexNet in 2012 ignited the deep learning (DL) revolution [3], followed by the rise of powerful open-source frameworks such as TensorFlow and PyTorch [4], which democratized access to advanced model development.”
Joint calibration of Ensemble of Exemplar SVMs
Modolo, D., Vezhnevets, A. S., Russakovsky, O., & Ferrari, V. (2015) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2015.7299021 · Cited by 7
Zhang, S. S., Wang, X., Lin, Y., et al. (2015) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2015.2478055 · Cited by 7
Incremental learning of latent structural SVM for weakly supervised image classification
Durand, T., Thome, N., Cord, M., et al. (2014) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2014.7025862 · Cited by 7
Huang, J., Qiu, Q., Calderbank, R., et al. (2015) · IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.471 · Cited by 7
Constrained Local Enhancement of Semantic Features by Content-Based Sparsity
Tamaazousti, Y., Borgne, H. L., & Popescu, A. (2016) · International Conference on Multimedia Retrieval · doi:10.1145/2911996.2912009 · Cited by 7
Self-restraint object recognition by model based CNN learning
Wang, Y., & Deng, W. (2016) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2016.7532438 · Cited by 7
Hierarchical Autoassociative Polynimial Network (HAP Net) for pattern recognition
Aspiras, T. H., & Asari, V. K. (2016) · Neurocomputing · doi:10.1016/j.neucom.2016.10.002 · Cited by 7
Improving deep convolutional neural networks with mixed maxout units
Zhao, H., Fu-xian, L., & Li, L. (2017) · PLoS ONE · doi:10.1371/journal.pone.0180049 · Cited by 7
Enhanced isomorphic semantic representation for cross-media retrieval
Liu, T., Zhao, Y., Wei, S., Wei, Y., & Liao, L. (2017) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2017.8019356 · Cited by 7
Deep visual gravity vector detection for unmanned aircraft attitude estimation
Ellingson, G. J., Wingate, D., & McLain, T. W. (2017) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2017.8206443 · Cited by 8
3D action recognition using multi-temporal skeleton visualization
Liu, M., Chen, C., Meng, F., et al. (2017) · IEEE International Conference on Multimedia & Expo Workshops (ICMEW) · doi:10.1109/icmew.2017.8026280 · Cited by 7
A Single Depth Sensor Based Human Activity Recognition via Convolutional Neural Network
Park, J. H., Park, S. U., Uddin, M. Z., Al–antari, M. A., Al‐masni, M. A., & Kim, T.-S. (2017) · World Congress on Medical Physics and Biomedical Engineering, September 7 - 12, 2009, Munich, Germany · doi:10.1007/978-981-10-4361-1_92 · Cited by 8
Interleaver design for deep neural networks
Dey, S., Beerei, P. A., & Chugg, K. M. (2017) · Asilomar Conference on Signals, Systems and Computers (ACSSC) · doi:10.1109/acssc.2017.8335713 · Cited by 7
Metadata
- Authors
- Krizhevsky, A., Sutskever, I., & Hinton, G. E.
- Affiliations
- Google (United States) (US)
- University of Toronto (CA)
- Venue
- Communications of the ACM
- Published
- 2017-05-24
- Volume
- 60
- Issue
- 6
- Pages
- 84-90
- ISSN
- 0001-0782 (ISSN-L)
- 1557-7317
- OpenAlex
- W2163605009
- Cited by
- 112,155
- References
- 27
- Citations by year
- 2026: 2710 · 2025: 7710 · 2024: 10211 · 2023: 12267 · 2022: 12280 · 2021: 15497 · 2020: 14538 · 2019: 13976 · 2018: 9999 · 2017: 6661
- FWCI
- 5127.18
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- Communications of the ACM (publishedVersion)
- neural information processing systems
- 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
- ImageNet, image classification, deep convolutional neural networks, dropout regularization, overfitting
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.
A language model drew the claims from the paper on 2026-10-11, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-11 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
