The DOI matches its Crossref record; 144 of the 157 references it cites were found in a registry or an index.
Efficient Processing of Deep Neural Networks: A Tutorial and Survey
Abstract
Deep neural networks (DNNs) are currently widely used for many artificial intelligence (AI) applications including computer vision, speech recognition, and robotics. While DNNs deliver state-of-the-art accuracy on many AI tasks, it comes at the cost of high computational complexity. Accordingly, techniques that enable efficient processing of DNNs to improve energy efficiency and throughput without sacrificing application accuracy or increasing hardware cost are critical to the wide deployment of DNNs in AI systems. This article aims to provide a comprehensive tutorial and survey about the recent advances toward the goal of enabling efficient processing of DNNs. Specifically, it will provide an overview of DNNs, discuss various hardware platforms and architectures that support DNNs, and highlight key trends in reducing the computation cost of DNNs either solely via hardware design changes or via joint hardware design and DNN algorithm changes. It will also summarize various development resources that enable researchers and practitioners to quickly get started in this field, and highlight important benchmarking metrics and design considerations that should be used for evaluating the rapidly growing number of DNN hardware designs, optionally including algorithmic codesigns, being proposed in academia and industry. The reader will take away the following concepts from this article: understand the key design considerations for DNNs; be able to evaluate different DNN hardware implementations with benchmarks and comparison metrics; understand the tradeoffs between various hardware architectures and platforms; be able to evaluate the utility of various DNN design techniques for efficient processing; and understand recent implementation trends and opportunities.
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
“Classical arithmetic operations, such as MAC, constitute the bulk of the computational requirements for models used in artificial intelligence [13].”
From Brain-inspired computing systems: a systematic literature review (2024) · cites this paper as [13]
In the citing paper
“To clarify, consider the multiply-and-accumulate (MAC) operation in digital processors, where the operation energy consumption is significantly dependent on the bit width of the input operands [13, 235] or equivalently to the signal-to-noise ratio (SNR) in analog computing [236].”
From Brain-inspired computing systems: a systematic literature review (2024) · cites this paper as [13]
In the citing paper
“Altogether, processing one 224 × 224 input image needs a VGG-16 model of 15.5 G multiply-and-accumulates and 138 M weights [40].”
From Face Recognition Based on Deep Learning and FPGA for Ethnicity Identification (2022) · cites this paper as [40]
In the citing paper
“The energy consumption of executing a DNN model is highly dictated by the computation architecture and methods (e.g., ultra-low power compute-in-memory AI accelerator) at the edge computation nodes [249], the architecture of DNN models [250], and the wireless transmission for data exchange during the model inference procedure.”
From Edge artificial intelligence for 6g: vision, enabling technologies, and applications (2022) · cites this paper as [250]
In the citing paper
“but there is no review discussing all three categories which in future will be integrated seamlessly to design effective and efficient DNNs in the new edge intelligence era.”
From Bringing ai to edge: from deep learning’s perspective (2022) · cites this paper as [25]
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 15×
“In 2015, the ImageNet winning entry, ResNet [15], exceeded human-level accuracy with a top-5 error rate4 below 5%.”
InfluentialVery Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148 · cited 10×
“Used in VGG-16. decompose 5x5 filter 5x1 filter 1x5 filter Apply sequentially (b) Constructing a 5×5 support from 1×5 and 5×1 filter.”
InfluentialImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · cited 10×
“this, local response normalization (LRN) [3] was used, which”
BackgroundMethodInfluentialHochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 1×
“In contrast, recurrent neural networks (RNNs), of which Long Short-Term Memory networks (LSTMs) [38] are a popular variant, have internal memory to allow long-term dependencies to affect the output.”
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805 · cited 4×
“Table 2 Summary of Popular DNNs [3], [15], [48], [50], [51]”
InfluentialGoing 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
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380 · cited 8×
“†ACCURACY IS MEASURED BASED ON TOP-5 ERROR ON IMAGENET [14].”
InfluentialFully convolutional networks for semantic segmentation
Long, J., Shelhamer, E., & Darrell, T. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298965 · Cited by 38,834
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.81 · Cited by 32,684
Research works printed but not linked: 34
- 10.13140/RG.2.2.18893.74727 · DOI · Paper page
- Li, Stanford CS Class CS231n: Convolutional Neural Networks for Visual Recognition
- 2016, Complete Visual Networking Index (VNI) Forecast
- Woodhouse, 2016, Big, Big, Big Data: Higher and Higher Resolution Video Surveillance
- Maas, Rectifier nonlinearities improve neural network acoustic models, 1
- Caffe LeNet MNIST
- Caffe Model Zoo
- Matconvnet Pretrained Models
- TensorFlow-Slim Image Classification Library
- Deep Learning Frameworks
- Yann, The MNIST DATABASE of Handwritten Digits
- Krizhevsky, The CIFAR-10 Dataset
- Krizhevsky, 2010, Convolutional deep belief networks on cifar-10, Unpublished Manuscript, 40, 1
- Pascal VOC Data Sets
- Microsoft Common Objects in Context (COCO) Dataset
- Google Open Images
- YouTube-8M
- AudioSet
- 2017, Intel Architecture Instruction Set Extensions Programming Reference
- Condon, Facebook unveils Big Basin, new server geared for deep learning
- Intel Math Kernel Library
- 10.1145/1816038.1815993 · DOI
- 10.1145/2872887.2750389 · DOI
- 10.1145/2644865.2541967 · DOI · Paper page
- Standard, High bandwidth memory (HBM) DRAM
- 10.1145/3093336.3037702 · DOI
- Wilson, International technology roadmap for semiconductors (ITRS)
- 10.1109/icvd.2004.1260946 · doi:10.1109/icvd.2004.1260946
- Lee, A 2.5 GHz 7.7 TOPS/W switched-capacitor matrix multiplier with co-designed local memory in 40 nm, 418
- Lee, LogNet: Energy-efficient neural networks using logrithmic computations, 5900
- DNN Energy Estimation
- 10.1145/3140659.3080254 · DOI · Paper page
- Iandola, SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <1 MB model size
- Benchmarking DNN Processors
Cited by
Items 201–300 of 1,011
Ho, S., Al-Jufout, S., Dajani, K. F., & Mozumdar, M. (2021) · IEEE Open Journal of the Computer Society · doi:10.1109/ojcs.2021.3050917 · Cited by 116
“For example, there are 78 features recorded for each traffic sample in the CICIDS2017 dataset, which can lead to high computational complexity for other deep learning models such as DNN [20].”
BackgroundInfluentialGreen Edge AI: A Contemporary Survey
Mao, Y., Yu, X., Huang, K., Zhang, Y. A., & Zhang, J. (2024) · Proceedings of the IEEE · doi:10.1109/jproc.2024.3437365 · Cited by 183
“V, mainly focus on software designs, and their benefits are greatly affected by the underlying hardware implementations [8].”
BackgroundInfluentialAdvances in UAV Path Planning: A Comprehensive Review of Methods, Challenges, and Future Directions
Meng, W., Zhang, X., Zhou, L., Guo, H., & Hu, X. (2025) · Drones · doi:10.3390/drones9050376 · Cited by 153
“For instance, Bae et al. [160] developed a multi-robot path planning algorithm that integrates Deep Q-learning with CNNs.”
Overfitting Mechanism and Avoidance in Deep Neural NetworksPreprint
Salman, S., & Liu, X. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.06566 · Cited by 310
Textual keyword extraction and summarization: State-of-the-art
Nasar, Z., Jaffry, S. W., & Malik, M. K. (2019) · Information Processing & Management · doi:10.1016/j.ipm.2019.102088 · Cited by 132
A tutorial on deep learning-based data analytics in manufacturing through a welding case study
Wang, Q., Jiao, W., Wang, P. E., & Zhang, Y. (2020) · Journal of Manufacturing Processes · doi:10.1016/j.jmapro.2020.04.044 · Cited by 125
Xu, W., Fang, W., Ding, Y., Zou, M., & Xiong, N. (2021) · IEEE Access · doi:10.1109/access.2021.3063291 · Cited by 112
“This would be very challenging and even intolerable for accomplishing all the performance evaluation experiments [4].”
BackgroundMethodInfluentialA Survey of Convolutional Neural Networks on Edge with Reconfigurable Computing
Véstias, M. P. (2019) · Algorithms · doi:10.3390/a12080154 · Cited by 134
Arpaïa, P., Espósito, A., Natalizio, A., & Parvis, M. (2022) · Journal of Neural Engineering · doi:10.1088/1741-2552/ac74e0 · Cited by 124
“Actually, deep neural networks are a subset of artificial ones in which more than one hidden layer is considered [111].”
Dave, S., Baghdadi, R., Nowatzki, T., Avancha, S., Shrivastava, A., & Li, B. (2021) · Proceedings of the IEEE · doi:10.1109/jproc.2021.3098483 · Cited by 140
“Surveys [28], [64]–[66] provide additional details about various layers used by different deep neural networks (DNNs) [67].”
BackgroundInfluentialXia, H., Tang, J., & Aljerf, L. (2022) · Chemosphere · doi:10.1016/j.chemosphere.2022.133716 · Cited by 110
Neuro-Detect: A Machine Learning-Based Fast and Accurate Seizure Detection System in the IoMT
Sayeed, M. A., Mohanty, S. P., Kougianos, E., & Zaveri, H. P. (2019) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2019.2917895 · Cited by 119
“In this work, a sigmoid transformation [51] has been used as an activation function: f (x) = 1 1 + e−x .”
MethodDesign possibilities and challenges of DNN models: a review on the perspective of end devices
Hussain, H., Tamizharasan, P. S., & Rahul, C. S. (2022) · Artificial Intelligence Review · doi:10.1007/s10462-022-10138-z · Cited by 140
“However, when evaluating system power, the off-chip memory access would be significant (Sze et al. 2017).”
BackgroundMachine Learning for Security in Vehicular Networks: A Comprehensive Survey
Talpur, A., & Gurusamy, M. (2022) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2021.3129079 · Cited by 107
“Another variant, deep neural network (DNN) is an ANN with deep (multiple) hidden layers [126].”
BackgroundAdderSR: Towards Energy Efficient Image Super-Resolution
Song, D., Wang, Y., Chen, H., Xu, C., Xu, C., & Tao, D. (2021) · 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/cvpr46437.2021.01539 · Cited by 130
“On the other hand, many research works [13, 31, 40] have indicated that add addition consumes fewer energy than multiplication.”
BackgroundMethodAccelerating CNN inference on FPGAs: A Survey
Abdelouahab, K., Pelcat, M., Serot, J., & Berry, F. (2018) · arXiv · doi:10.48550/arxiv.1806.01683 · Cited by 107
“This redundancy, as pointed-out in [12], can lead to either inefficiency in storage or complex memory access patterns.”
InfluentialAI and ML Accelerator Survey and Trends
Reuther, A., Michaleas, P., Jones, M., Gadepally, V., Samsi, S., & Kepner, J. (2022) · 2022 IEEE High Performance Extreme Computing Conference (HPEC) · doi:10.1109/hpec55821.2022.9926331 · Cited by 109
PolySA: polyhedral-based systolic array auto-compilation
Cong, J., & Wang, J. (2018) · doi:10.1145/3240765.3240838 · Cited by 113
A survey on hardware accelerators: Taxonomy, trends, challenges, and perspectives
Peccerillo, B., Mannino, M., Mondelli, A., & Bartolini, S. (2022) · Journal of Systems Architecture · doi:10.1016/j.sysarc.2022.102561 · Cited by 148
Shafique, M., Theocharides, T., Bouganis, C.-S., Hanif, M. A., Khalid, F., Hafiz, R., & Rehman, S. (2018) · Design, Automation, and Test in Europe · doi:10.23919/date.2018.8342120 · Cited by 109
Training deep neural networks for binary communication with the Whetstone method
Severa, W., Vineyard, C. M., Dellana, R., Verzi, S., & Aimone, J. B. (2019) · Nature Machine Intelligence · doi:10.1038/s42256-018-0015-y · Cited by 123
Frenkel, C., Bol, D., & Indiveri, G. (2023) · Proceedings of the IEEE · doi:10.1109/jproc.2023.3273520 · Cited by 190
Drug-drug interactions prediction based on deep learning and knowledge graph: A review
Luo, H., Yin, W., Wang, J., Zhang, G., Liang, W., Luo, J., & Yan, C. (2024) · iScience · doi:10.1016/j.isci.2024.109148 · Cited by 128
Koppula, S., Orosa, L., Yağlıkçı, A. G., Azizi, R., Shahroodi, T., Kanellopoulos, K., & Mutlu, O. (2019) · IEEE/ACM International Symposium on Microarchitecture (MICRO) · doi:10.1145/3352460.3358280 · Cited by 137
“By using the accelerator/network/cache/DRAM energy breakdown provided by the Eyeriss evaluations on AlexNet [161], we estimate that EDEN can provide 26.”
MethodKumar, P. S., Behera, H. S., Anisha Kumari, K., Nayak, J., & Naik, B. (2020) · Computer Science Review · doi:10.1016/j.cosrev.2020.100288 · Cited by 105
Normalization in Training U-Net for 2-D Biomedical Semantic Segmentation
Zhou, X.-Y., & Yang, G. (2019) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2019.2896518 · Cited by 117
“It is known that training the same model in multiple times indicate different results - 2% variance as stated in [21].”
BackgroundResultInfluentialLiu, X., Miao, X., Jiang, H., & Chen, J. (2020) · Annual Reviews in Control · doi:10.1016/j.arcontrol.2020.09.002 · Cited by 139
Spiking Neural Network Integrated Circuits: A Review of Trends and Future Directions
Basu, A., Deng, L., Frenkel, C., & Zhang, X. (2022) · Custom Integrated Circuits Conference · doi:10.1109/cicc53496.2022.9772783 · Cited by 146
Soft errors in DNN accelerators: A comprehensive review
Ibrahim, Y., Wang, H., Liu, J., Wei, J., Chen, L., Rech, P., Adam, K., & Guo, G. (2020) · Microelectronics Reliability · doi:10.1016/j.microrel.2020.113969 · Cited by 102
Blanco‐Filgueira, B., García-Lesta, D., Fernández-Sanjurjo, M., Brea, V. M., & Lopez, P. (2019) · IEEE Internet of Things Journal · doi:10.1109/jiot.2019.2902141 · Cited by 112
Bi-Real Net: Binarizing Deep Network Towards Real-Network Performance
Liu, Z., Luo, W., Wu, B., Yang, X., Liu, W., & Cheng, K.-T. T. (2019) · International Journal of Computer Vision · doi:10.1007/s11263-019-01227-8 · Cited by 124
“An overview of neural network compression and acceleration from both the hardware and software perspectives is provided in [35].”
Machine Learning for Healthcare-IoT Security: A Review and Risk Mitigation
Khatun, M. A., Memon, S. F., Eising, C., & Dhirani, L. L. (2023) · IEEE Access · doi:10.1109/access.2023.3346320 · Cited by 179
“Furthermore, the downsampling process, which is more precise than average pooling, preserves texture information by minimizing the differences in evaluation values resulting from the convolutional layers [253], [254].”
BackgroundOptimizing Deeper Spiking Neural Networks for Dynamic Vision Sensing
Kim, Y., & Panda, P. (2021) · Neural Networks · doi:10.1016/j.neunet.2021.09.022 · Cited by 105
Computerized Ultrasonic Imaging Inspection: From Shallow to Deep Learning
Ye, J., Ito, S., & Toyama, N. (2018) · Sensors · doi:10.3390/s18113820 · Cited by 108
“Among them, well-developed CNNs, such as AlexNet, VGG-16, and ResNet architectures, emerged as standard approaches to visual tasks [35].”
MethodVinothini, A., Ghanimi, H. M. A., Pustokhin, D. A., Pustokhina, I. V., Sagar, P. V., Alharbi, M., Krishnamoorthy, P., & Sengan, S. (2023) · Sustainability · doi:10.3390/su15065453 · Cited by 98
Ikram, A., Mehmood, H., Arshad, M. T., Rasheed, A., Noreen, S., & Gnedeka, K. T. (2024) · CyTA - Journal of Food · doi:10.1080/19476337.2024.2393287 · Cited by 118
“Efficient processing of AI analytics and dense, deep neural networks (DNNs) is critical for enhancing energy efficiency without incurring additional hardware expenditures (Sza et al., 2017).”
DRQ: Dynamic Region-based Quantization for Deep Neural Network Acceleration
Song, Z., Fu, B., Wu, F., Jiang, Z., Jiang, L., Jing, N., & Liang, X. (2020) · Proceedings - International Symposium on Computer Architecture/Proceedings · doi:10.1109/isca45697.2020.00086 · Cited by 130
“In the last few years, various NN accelerators are proposed for inference [4], [6], [8], [11], [13], [18], [28], [30], [36].”
BackgroundAI Accelerator Survey and Trends
Reuther, A., Michaleas, P. W., Jones, M. P., Gadepally, V. N., Samsi, S., & Kepner, J. (2021) · IEEE High Performance Extreme Computing Conference · doi:10.1109/hpec49654.2021.9622867 · Cited by 105
“Research chips including Eyeriss [16], [126], [127], EIE [128], Tetris [129], Tian-jic [130], the DianNao family [131], Adapteva [132], [133], and NeuFlow [134] have been important in showing various computational performance, energy efficiency, and computational accuracy gains that could be…”
BackgroundAn FPGA Implementation of Deep Spiking Neural Networks for Low-Power and Fast Classification
Ju, X., Fang, B., Yan, R., Xu, X., & Tang, H. (2019) · Neural Computation · doi:10.1162/neco_a_01245 · Cited by 107
Communication-Efficient Distributed Deep Learning: A Comprehensive SurveyPreprint
Tang, Z., Shi, S., Wang, W., Li, B., & Chu, X. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.06307 · Cited by 202
“In order to reduce the training time, on the one hand, the computing power of a single accelerator should be fully utilized by using highly optimized software implementation [11][12][13][14][15].”
MethodDevice-Circuit-Architecture Co-Exploration for Computing-in-Memory Neural Accelerators
Jiang, W., Lou, Q., Yan, Z., Yang, L., Hu, J., Hu, X. S., & Shi, Y. (2021) · IEEE Transactions on Computers · doi:10.1109/tc.2020.2991575 · Cited by 96
“(i) CiM architecture can benefit from the fixed memory access pattern within neural network computation [26] to execute operations in place.”
BackgroundSilicon Photonics Codesign for Deep Learning
Cheng, Q., Kwon, J., Glick, M. S., Bahadori, M., Carloni, L. P., & Bergman, K. (2020) · Proceedings of the IEEE · doi:10.1109/jproc.2020.2968184 · Cited by 108
“Meanwhile, much research has also been conducted on the accelerated and efficient computation of DNNs [16].”
Backgroundİlhan, H. O., Sığırcı, I. O., Serbes, G., & Aydın, N. (2020) · Medical & Biological Engineering & Computing · doi:10.1007/s11517-019-02101-y · Cited by 100
Scaling up silicon photonic-based accelerators: Challenges and opportunities
Al-Qadasi, M. A., Chrostowski, L., Shastri, B. J., & Shekhar, S. (2022) · APL Photonics · doi:10.1063/5.0070992 · Cited by 94
Wang, H., Shao, W., Sun, C., Yang, K., Cao, D., & Li, J. (2024) · Engineering · doi:10.1016/j.eng.2023.10.011 · Cited by 122
Pedestrian Detection in Severe Weather Conditions
Tumas, P., Nowosielski, A., & Serackis, A. (2020) · IEEE Access · doi:10.1109/access.2020.2982539 · Cited by 100
“According to research [13], [14], the accuracy of the detector may vary on the variety of dataset samples, detector input/type used, and implementation details.”
BackgroundOn the Resilience of RTL NN Accelerators: Fault Characterization and Mitigation
Salami, B., Ünsal, O., & Kestelman, A. C. (2018) · International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD) · doi:10.1109/cahpc.2018.8645906 · Cited by 114
Zhao, T., Xie, Y., Wang, Y., Cheng, J., Guo, X., Hu, B., & Chen, Y. J. (2022) · Proceedings of the IEEE · doi:10.1109/jproc.2022.3153408 · Cited by 129
Self-citationUniversal Deep Neural Network Compression
Choi, Y., El‐Khamy, M., & Lee, J. (2020) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2020.2975903 · Cited by 111
“, see [4], [5]).”
Image representation of pose-transition feature for 3D skeleton-based action recognition
Huynh‐The, T., Hua, C.-H., Ngo, T.-T., & Kim, D. (2019) · Information Sciences · doi:10.1016/j.ins.2019.10.047 · Cited by 92
A TinyML Platform for On-Device Continual Learning With Quantized Latent Replays
Ravaglia, L., Rusci, M., Nadalini, D., Capotondi, A., Conti, F., & Benini, L. (2021) · IEEE Journal on Emerging and Selected Topics in Circuits and Systems · doi:10.1109/jetcas.2021.3121554 · Cited by 132
A deep learning approach for optimizing content delivering in cache-enabled HetNet
Lei, L., You, L., Dai, G., Vu, T. X., Yuan, D., & Chatzinotas, S. (2017) · International Symposium on Wireless Communication Systems · doi:10.1109/iswcs.2017.8108157 · Cited by 91
Breast Cancer Detection Using Transfer Learning in Convolutional Neural Networks
Guan, S., & Loew, M. H. (2017) · IEEE Applied Imagery Pattern Recognition Workshop · doi:10.1109/aipr.2017.8457948 · Cited by 94
“The CNN has performed well in many image classification tasks [7].”
MethodFeng, J., Chen, J., Sun, Q., Shang, R., Cao, X., Zhang, X., & Jiao, L. (2020) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2020.3000725 · Cited by 90
Jauro, F., Chiroma, H., Gital, A. Y., Almutairi, M. S., Abdulhamid, S. M., & Abawajy, J. (2020) · Applied Soft Computing · doi:10.1016/j.asoc.2020.106582 · Cited by 114
Accelerating CNN Inference on ASICs: A Survey
Moolchandani, D., Kumar, A., & Sarangi, S. R. (2020) · Journal of Systems Architecture · doi:10.1016/j.sysarc.2020.101887 · Cited by 107
“Effective caching of data in on-chip buffers has been shown to reduce the number of off-chip accesses by up to 500X [117].”
BackgroundMethodInfluentialDeep Reinforcement Learning for Semisupervised Hyperspectral Band Selection
Feng, J., Li, D., Gu, J., Cao, X., Shang, R., Zhang, X., & Jiao, L. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3049372 · Cited by 93
“In this part, the computational complexity is analyzed by measuring the number of learnable parameters and floating point operations (FLOPs) [46], [47].”
BackgroundEdge Intelligence: A Review of Deep Neural Network Inference in Resource-Limited Environments
Ngo, D., Park, H.-C., & Kang, B. (2025) · Electronics · doi:10.3390/electronics14122495 · Cited by 151
Zhang, C., Li, R., & Wang, Q. (2025) · Renewable and Sustainable Energy Reviews · doi:10.1016/j.rser.2025.116574 · Cited by 119
Stealing Neural Networks via Timing Side ChannelsPreprint
Duddu, V., Samanta, D., Rao, D. V., & Bălaş, V. E. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1812.11720 · Cited by 172
“During inference, CPUs and Neural Network accelerators are extensively used while GPUs are used for training Neural Network architectures [37].”
BackgroundMethodSemantic Segmentation of Underwater Images Based on Improved Deeplab
Liu, F., & Fang, M. (2020) · Journal of Marine Science and Engineering · doi:10.3390/jmse8030188 · Cited by 90
A Full Featured Configurable Accelerator for Object Detection With YOLO
Pestana, D. G., Miranda, P. R., Lopes, J. D., Duarte, R. P., Véstias, M. P., Neto, H. C., & de Sousa, J. T. (2021) · IEEE Access · doi:10.1109/access.2021.3081818 · Cited by 102
“However, pooling layers are more robust as they turn the network invariant to small shifts and distortions when downsampling [18].”
BackgroundMethodInfluentialBeyond classification: directly training spiking neural networks for semantic segmentation
Kim, Y., Chough, J., & Panda, P. (2022) · Neuromorphic Computing and Engineering · doi:10.1088/2634-4386/ac9b86 · Cited by 136
Freire, P. J., Srivallapanondh, S., Spinnler, B., Napoli, A., Costa, N. M. S., Prilepsky, J. E., & Turitsyn, S. K. (2024) · Journal of Lightwave Technology · doi:10.1109/jlt.2024.3386886 · Cited by 118
“…that refers to the absence of some “universal” measure, various works started to present complexity in terms of multiply and accumulate (MAC) [19], [20], [21], [22], Kolmogorov complexity [23], the number of bit-operations (BOP) [24], [25], the number of real multiplications (RM) [26], [27],…”
BackgroundCheckmate: Breaking the Memory Wall with Optimal Tensor RematerializationPreprint
Jain, P., Jain, A., Nrusimha, A., Gholami, A., Abbeel, P., Keutzer, K., Stoica, I. G., & Gonzalez, J. E. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.02653 · Cited by 131
“In practice, DNN layers vary significantly in memory usage and computational cost (Sze et al., 2017), so these heuristics are not optimal in practice.”
BackgroundEnergy-Efficient Stochastic Computing with Superparamagnetic Tunnel Junctions
Daniels, M. W., Madhavan, A., Talatchian, P., Mizrahi, F. A., & Stiles, M. D. (2020) · Physical Review Applied · doi:10.1103/physrevapplied.13.034016 · Cited by 100
“[77] V.”
BackgroundPANTHER: A Programmable Architecture for Neural Network Training Harnessing Energy-Efficient ReRAM
Ankit, A., Hajj, I. E., Chalamalasetti, S. R., Agarwal, S., Marinella, M. J., Foltín, M., Strachan, J. P., Milojicic, D. S., Hwu, W., & Roy, K. (2020) · IEEE Transactions on Computers · doi:10.1109/tc.2020.2998456 · Cited by 88
Reconfigurable Compute-In-Memory on Field-Programmable Ferroelectric Diodes
Liu, X., Ting, J., He, Y., Fiagbenu, M. M. A., Zheng, J. X., Wang, D., Frost, J., Musavigharavi, P., Esteves, G., Kisslinger, K., et al. (2022) · Nano Letters · doi:10.1021/acs.nanolett.2c03169 · Cited by 97
“The increasingly ubiquitous presence of sensors and edge/IoT devices has created a flood of data, which has exposed a wide efficiency gap in computing hardware, ranging from mobile and edge devices to data centers and cloud computing hardware [4-5].”
BackgroundThe Impact of GPU DVFS on the Energy and Performance of Deep Learning: an Empirical Study
Tang, Z., Wang, Y., Wang, Q., & Chu, X. (2019) · Proceedings of the Tenth ACM International Conference on Future Energy Systems · doi:10.1145/3307772.3328315 · Cited by 88
“Some studies [25] indicated that the computation of convolution layers usually dominate the training time.”
BackgroundAutomated detection of COVID-19 cough
Tena, A., Claria, F., & Solsona, F. (2021) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2021.103175 · Cited by 107
“The MobileNet structure is built on depthwise separable convolutions which factorises a standard convolution into a depthwise and a pointwise convolution (1 x 1 convolution kernel) [26].”
All‐optical ultrafast ReLU function for energy‐efficient nanophotonic deep learning
Li, G. H. Y., Sekine, R., Nehra, R., Gray, R. M., Ledezma, L. M., Guo, Q., & Marandi, A. (2022) · Nanophotonics · doi:10.1515/nanoph-2022-0137 · Cited by 115
Sustainable Deep Learning at Grid Edge for Real-Time High Impedance Fault Detection
Sirojan, T., Lu, S., Phung, B. T., Zhang, D., & Ambikairajah, E. (2018) · IEEE Transactions on Sustainable Computing · doi:10.1109/tsusc.2018.2879960 · Cited by 100
Efficient Federated Learning for Cloud-Based AIoT Applications
Zhang, X., Hu, M., Xia, J., Wei, T., Chen, M., & Hu, S. (2020) · IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems · doi:10.1109/tcad.2020.3046665 · Cited by 105
Zheng, L., Long, M., Niu, J., & Zhong, L. (2023) · International Journal of Computer-Supported Collaborative Learning · doi:10.1007/s11412-023-09386-0 · Cited by 115
“Deep Neural Networks (DNNs) are the neural networks used in deep learning (Sze et al., 2017).”
BackgroundThe Final Frontier: Deep Learning in Space
Kothari, V., Liberis, E., & Lane, N. D. (2020) · Proceedings of the 21st International Workshop on Mobile Computing Systems and Applications · doi:10.1145/3376897.3377864 · Cited by 86
“The uptake of off-the-shelf components, would allows us to leverage recent developments in compute efficient (quantized) [40], memory sensitive (compressed) [26], and energy aware [46] terrestrial DL models.”
BackgroundWu, T. F., Li, H., Huang, P.-C., Rahimi, A., Hills, G., Hodson, B., Hwang, W., Rabaey, J. M., Wong, H. ‐. P., Shulaker, M. M., et al. (2018) · IEEE Journal of Solid-State Circuits · doi:10.1109/jssc.2018.2870560 · Cited by 92
Explicit Loss-Error-Aware Quantization for Low-Bit Deep Neural Networks
Zhou, A., Yao, A., Wang, K., & Chen, Y. (2018) · 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.2018.00982 · Cited by 101
“In the literature, there exists numerous methods for DNN compression and acceleration, and the reader is referred to [34] for a recent survey.”
MethodSelf-citationAnwar, A., & Raychowdhury, A. (2020) · IEEE Access · doi:10.1109/access.2020.2971172 · Cited by 109
“The first and more direct approach is to make better hardware engines for DNN accelerators [9], [10].”
BackgroundReview of Automatic Detection and Classification Techniques for Cetacean Vocalization
Usman, A. M., Ogundile, O. O., & Versfeld, D. J. J. (2020) · IEEE Access · doi:10.1109/access.2020.3000477 · Cited by 88
“Comprehensive tutorials on NNs have been explained in [111], [112], [115].”
BackgroundAn Overview of Efficient Interconnection Networks for Deep Neural Network Accelerators
Nabavinejad, S. M., Baharloo, M. M., Chen, K.-C. J., Palesi, M., Kogel, T., & Ebrahimi, M. (2020) · IEEE Journal on Emerging and Selected Topics in Circuits and Systems · doi:10.1109/jetcas.2020.3022920 · Cited by 95
“The notable benefits of AI have led to the advancement in many real-world applications, such as speech recognition and image classification [1].”
BackgroundArtificial neural networks for photonic applications—from algorithms to implementation: tutorial
Freire, P. J., Manuylovich, E. S., Prilepsky, J. E., & Turitsyn, S. K. (2023) · Advances in Optics and Photonics · doi:10.1364/aop.484119 · Cited by 111
FIdelity: Efficient Resilience Analysis Framework for Deep Learning Accelerators
He, Y., Balaprakash, P., & Li, Y. (2020) · 2020 53rd Annual IEEE/ACM International Symposium on Microarchitecture (MICRO) · doi:10.1109/micro50266.2020.00033 · Cited by 83
“The sequencing order is determined by the specific scheduling and dataflow (reuse) algorithm (e.g., weight reuse, row stationary, etc. [23]).”
BackgroundMethodLane-DeepLab: Lane semantic segmentation in automatic driving scenarios for high-definition maps
Li, J., Jiang, F., Yang, J., Kong, B., Gogate, M., Dashtipour, K. K., & Hussain, A. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.08.105 · Cited by 98
A Survey on Deep-Learning-Based Real-Time SAR Ship Detection
Li, J., Chen, J., Cheng, P., Yu, Z., Yu, L., & Chi, C. (2023) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2023.3244616 · Cited by 98
“1 [12].”
Nandakumar, S. R., Boybat, I., Gallo, M. L., Eleftheriou, E. S., Sebastian, A., & Rajendran, B. (2020) · Scientific Reports · doi:10.1038/s41598-020-64878-5 · Cited by 98
Review of ASIC accelerators for deep neural network
Machupalli, R., Hossain, M., & Mandal, M. K. (2022) · Microprocessors and Microsystems · doi:10.1016/j.micpro.2022.104441 · Cited by 108
A Systematic Literature Review on Hardware Reliability Assessment Methods for Deep Neural Networks
Ahmadilivani, M. H., Taheri, M., Raik, J., Daneshtalab, M., & Jenihhin, M. (2023) · ACM Computing Surveys · doi:10.1145/3638242 · Cited by 132
“Equation (1) represents the function of the i th neuron in layer l (denoted as N li ) with input activations from the previous layer l-1 with n outputs (denoted as X l − 1 ), where W and b represent weights and bias, respectively.”
BackgroundMethodInfluentialLiu, L., Wang, D., Wang, D., Sun, Y., Lin, H., Gong, X., Zhang, Y., Tang, R., Mai, Z., Hou, Z., et al. (2024) · Nature Communications · doi:10.1038/s41467-024-48631-4 · Cited by 111
Real-Time AI-Based Anomaly Detection and Classification in Power Electronics Dominated Grids
Baker, M., Fard, A. Y., Althuwaini, H., & Shadmand, M. B. (2022) · IEEE Journal of Emerging and Selected Topics in Industrial Electronics · doi:10.1109/jestie.2022.3227005 · Cited by 97
“employs an internal memory to create the predictions for next steps of the system [29], a perfect match to be integrated with”
BackgroundA Survey of Next-generation Computing Technologies in Space-air-ground Integrated Networks
Shen, Z., Jin, J., Tan, C., Tagami, A., Wang, S., Li, Q., Zheng, Q., & Yuan, J. (2023) · ACM Computing Surveys · doi:10.1145/3606018 · Cited by 111
“Various platforms that perform DNN inference have stringent energy consumption, computation and memory cost limitations [154].”
BackgroundArtificial intelligence facilitates drug design in the big data era
Wang, L., Ding, J., Pan, L., Cao, D., Jiang, H., & Ding, X. (2019) · Chemometrics and Intelligent Laboratory Systems · doi:10.1016/j.chemolab.2019.103850 · Cited by 80
Freely scalable and reconfigurable optical hardware for deep learning
Bernstein, L., Sludds, A., Hamerly, R., Sze, V., Emer, J., & Englund, D. (2020) · Scientific Reports · doi:10.1038/s41598-021-82543-3 · Cited by 80
Self-citationTowards efficient communications in federated learning: A contemporary survey
Zhao, Z., Mao, Y., Liu, Y., Song, L., Ouyang, Y., Chen, X., & Ding, W. (2023) · Journal of the Franklin Institute · doi:10.1016/j.jfranklin.2022.12.053 · Cited by 121
Towards Trustworthy AI: A Review of Ethical and Robust Large Language Models
Ferdaus, M. M., Abdelguerfi, M., Ioup, E., Niles, K. N., Pathak, K., & Sloan, S. (2024) · arXiv · doi:10.48550/arxiv.2407.13934 · Cited by 80
Learning-Based Frequency Estimation Algorithms.
Hsu, C.-Y., Indyk, P., Katabi, D., & Vakilian, A. (2018) · DSpace@MIT (Massachusetts Institute of Technology) · Cited by 116
Shrivastava, K., Kumar, S., & Jain, D. K. (2019) · Multimedia Tools and Applications · doi:10.1007/s11042-019-07813-9 · Cited by 90
Shredder: Learning Noise Distributions to Protect Inference Privacy
Mireshghallah, F., Taram, M., Ramrakhyani, P., Jalali, A., Tullsen, D. M., & Esmaeilzadeh, H. (2020) · International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS) · doi:10.1145/3373376.3378522 · Cited by 133
“The increasing processing demand of learningmodels [4, 5] has naturally pushed most of the computation to the cloud [6].”
BackgroundMaking Convolutions Resilient Via Algorithm-Based Error Detection Techniques
Hari, S. K. S., Sullivan, M. B., Tsai, T. K., & Keckler, S. W. (2021) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2021.3063083 · Cited by 87
An Attention-Based Deep Learning Framework for Trip Destination Prediction of Sharing Bike
Wang, W. W., Zhao, X., Gong, Z., Chen, Z., Zhang, N., & Wei, W. (2020) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2020.3008935 · Cited by 86
Halide Perovskite Quantum Dots Photosensitized‐Amorphous Oxide Transistors for Multimodal Synapses
Periyal, S. S., Jagadeeswararao, M., Ng, S. E., John, R. A., & Mathews, N. (2020) · Advanced Materials Technologies · doi:10.1002/admt.202000514 · Cited by 81
Metadata
- Authors
- Sze, V., Chen, Y.-H., Yang, T.-J., & Emer, J. S.
- Affiliations
- Massachusetts Institute of Technology (US)
- Nvidia (United States) (US)
- Venue
- Proceedings of the IEEE
- Published
- 2017-12
- Volume
- 105
- Issue
- 12
- Pages
- 2295-2329
- ISSN
- 0018-9219 (ISSN-L)
- 1558-2256
- OpenAlex
- W2604319603
- Cited by
- 4,215
- References
- 157
- Citations by year
- 2026: 504 · 2025: 523 · 2024: 474 · 2023: 466 · 2022: 508 · 2021: 568 · 2020: 551 · 2019: 392 · 2018: 199 · 2017: 28
- FWCI
- 132.75
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Proceedings of the IEEE (publishedVersion)
- Funders
- DARPA YFA
- MIT CICS
- gift from Nvidia
- gift from Intel
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Hardware and Architecture › Parallel Computing and Optimization Techniques
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced Memory and Neural Computing
- Keywords
- deep neural network, energy efficiency, throughput, hardware accelerators, computation cost reduction, benchmarking metrics
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.