DeepX: A Software Accelerator for Low-Power Deep Learning Inference on Mobile Devices
Open accessThe DOI matches its Crossref record; 34 of the 34 references it cites were found in a registry or an index.
Abstract
Breakthroughs from the field of deep learning are radically changing how sensor data are interpreted to extract the high-level information needed by mobile apps. It is critical that the gains in inference accuracy that deep models afford become embedded in future generations of mobile apps. In this work, we present the design and implementation of DeepX, a software accelerator for deep learning execution. DeepX signif- icantly lowers the device resources (viz. memory, computation, energy) required by deep learning that currently act as a severe bottleneck to mobile adoption. The foundation of DeepX is a pair of resource control algorithms, designed for the inference stage of deep learning, that: (1) decompose monolithic deep model network architectures into unit- blocks of various types, that are then more efficiently executed by heterogeneous local device processors (e.g., GPUs, CPUs); and (2), perform principled resource scaling that adjusts the architecture of deep models to shape the overhead each unit-blocks introduces. Experiments show, DeepX can allow even large-scale deep learning models to execute efficently on modern mobile processors and significantly outperform existing solutions, such as cloud-based offloading.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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
“The work in [205] introduces a software-based deep learning accelerator to support AI/DL training on mobile hardware.”
From Federated Learning for Internet of Things: A Comprehensive Survey (2021) · cites this paper as [205]
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
“Simulation results demonstrates its superior performance in terms of low execution time and energy consumption in AI hardware running, compared to cloud offloading-based approaches.”
From Federated Learning for Internet of Things: A Comprehensive Survey (2021) · cites this paper as [205]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
ImageNet 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
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
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
A fast learning algorithm for deep belief nets
Hinton, G. E., Osindero, S., & Teh, Y.-W. (2006) · Neural Computation · doi:10.1162/neco.2006.18.7.1527 · Cited by 16,336
Hinton, G., Deng, L., Yu, D., Dahl, G., Mohamed, A.-R., Jaitly, N., Senior, A., Vanhoucke, V., Nguyen, P., Sainath, T., et al. (2012) · IEEE Signal Processing Magazine · doi:10.1109/msp.2012.2205597 · Cited by 10,260
Pattern Recognition and Machine Learning
(2006) · doi:10.1007/978-0-387-45528-0 · Cited by 9,824
(2006) · Springer eBooks · Cited by 8,123
DeepFace: Closing the Gap to Human-Level Performance in Face Verification
Taigman, Y., Yang, M., Ranzato, M., & Wolf, L. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.220 · Cited by 6,542
Large Scale Distributed Deep Networks
Dean, J. B., Corrado, G. S., Monga, R., Chen, K., Devin, M., Mao, M., Ranzato, M., Senior, A., Tucker, P. A., Yang, K., et al. (2012) · neural information processing systems · Cited by 4,489
Reading digits in natural images with unsupervised feature learning
Netzer, Y. (2024) · doi:10.57702/e7wwo0zk · Cited by 4,149
Optimizing FPGA-based Accelerator Design for Deep Convolutional Neural Networks
Zhang, C., Li, P., Sun, G., Guan, Y., Xiao, B., & Cong, J. (2015) · Proceedings of the 2015 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays · doi:10.1145/2684746.2689060 · Cited by 2,158 · cited 2×
“Although, DeepX is not tested on purpose built hardware for deep learning [41], [45], our software approach to accelerating models in general should apply in this case.”
BackgroundMethodDianNao: a small-footprint high-throughput accelerator for ubiquitous machine-learning
Chen, T., Du, Z., Sun, N., Wang, J., Wu, C., Chen, Y., & Temam, O. (2014) · Proceedings of the 19th international conference on Architectural support for programming languages and operating systems · doi:10.1145/2541940.2541967 · Cited by 1,297
Deep neural networks for small footprint text-dependent speaker verification
Variani, E., Lei, X., McDermott, E., Moreno, I. L., & Gonzalez-Dominguez, J. (2014) · 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2014.6854363 · Cited by 1,035
Compressing Deep Convolutional Networks using Vector Quantization
Gong, Y., Liu, L., Yang, M., & Bourdev, L. D. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1412.6115 · Cited by 925
A resource management architecture for metacomputing systems
Czajkowski, K., Foster, I., Karonis, N., Kesselman, C., Martin, S., Smith, W., & Tuecke, S. (1998) · Lecture Notes in Computer Science · doi:10.1007/bfb0053981 · Cited by 782
Small-footprint keyword spotting using deep neural networks
Chen, G., Parada, C., & Heigold, G. (2014) · 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2014.6854370 · Cited by 545
StressSense: detecting stress in unconstrained acoustic environments using smartphones
Lu, H., Frauendorfer, D., Rabbi, M., Mast, M. S., Chittaranjan, G. T., Campbell, A. T., Gatica-Perez, D., & Choudhury, T. (2012) · Proceedings of the 2012 ACM Conference on Ubiquitous Computing · doi:10.1145/2370216.2370270 · Cited by 511
EmotionSense: a mobile phones based adaptive platform for experimental social psychology research
Rachuri, K. K., Musolesi, M., Mascolo, C., Rentfrow, P. J., Longworth, C., & Aucinas, A. (2010) · Proceedings of the 12th ACM international conference on Ubiquitous computing · doi:10.1145/1864349.1864393 · Cited by 508
Restructuring of deep neural network acoustic models with singular value decomposition
Xue, J., Li, J., & Gong, Y. (2013) · Interspeech 2013 · doi:10.21437/interspeech.2013-552 · Cited by 407
Deep learning for robust feature generation in audiovisual emotion recognition
Kim, Y., Lee, H., & Provost, E. M. (2013) · 2013 IEEE International Conference on Acoustics, Speech and Signal Processing · doi:10.1109/icassp.2013.6638346 · Cited by 401 · cited 1×
“The range of inference tasks impacted by deep learning includes the recognition of: faces [2], emotions [3], objects [4] and words [5].”
BackgroundDeepEar: robust smartphone audio sensing in unconstrained acoustic environments using deep learning
Lane, N. D., Georgiev, P., & Qendro, L. (2015) · Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing · doi:10.1145/2750858.2804262 · Cited by 310
Self-citationCan Deep Learning Revolutionize Mobile Sensing?
Lane, N. D., & Georgiev, P. (2015) · Proceedings of the 16th International Workshop on Mobile Computing Systems and Applications · doi:10.1145/2699343.2699349 · Cited by 282 · cited 2×
“However, deep models need resource optimization before they can even execute on a mobile platform [43]; many deep models have memory requirements that are too high for a mobile SoC to support.”
BackgroundSelf-citationLane, N. D., Bhattacharya, S., Georgiev, P., Forlivesi, C., & Kawsar, F. (2015) · Proceedings of the 2015 International Workshop on Internet of Things towards Applications · doi:10.1145/2820975.2820980 · Cited by 228
Self-citationDarwin phones: the evolution of sensing and inference on mobile phones
Miluzzo, E., Cornelius, C. T., Ramaswamy, A., Choudhury, T., Liu, Z., & Campbell, A. T. (2010) · Proceedings of the 8th international conference on Mobile systems, applications, and services · doi:10.1145/1814433.1814437 · Cited by 200
BeWell: Sensing Sleep, Physical Activities and Social Interactions to Promote Wellbeing
Lane, N. D., Lin, M., Mohammod, M., Yang, X., Lu, H., Cardone, G., Ali, S., Doryab, A., Berke, E., Campbell, A. T., et al. (2014) · Mobile Networks and Applications · doi:10.1007/s11036-013-0484-5 · Cited by 172
Self-citationHistogram of gradients of Time-Frequency Representations for Audio Scene Detection
Rakotomamonjy, A., & Gasso, G. (2014) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2014.2375575 · Cited by 171
SpeakerSense: Energy Efficient Unobtrusive Speaker Identification on Mobile Phones
Lu, H., Brush, A. J. B., Priyantha, N. B., Karlson, A. K., & Liu, J. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-21726-5_12 · Cited by 155
Balancing energy, latency and accuracy for mobile sensor data classification
Chu, D. C. Y., Lane, N. D., Lai, T. T.-T., Pang, C., Meng, X., Guo, Q., Li, F., & Zhao, F. (2011) · ACM Conference on Embedded Networked Sensor Systems (SenSys) · doi:10.1145/2070942.2070949 · Cited by 120
Self-citationReshaping deep neural network for fast decoding by node-pruning
He, T., Fan, Y., Qian, Y., Tan, T., & Yu, K. (2014) · 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2014.6853595 · Cited by 113
Predicting the CPU availability of time-shared Unix systems on the computational grid
Wolski, R., Spring, N. T., & Hayes, J. (2003) · ACM International Symposium on High-Performance Parallel and Distributed Computing (HPDC) · doi:10.1109/hpdc.1999.805288 · Cited by 111
Yamagishi, J., Massimiliano, T., Sahidullah, M., Delgado, H., Wang, X., Evans, N., Kinnunen, T., Lee, K. A., Vestman, V., & Nautsch, A. (2015) · UEF eRepo (University of Eastern Finland) · doi:10.7488/ds/298 · Cited by 85
DSP.Ear: leveraging co-processor support for continuous audio sensing on smartphones
Georgiev, P., Lane, N. D., Rachuri, K. K., & Mascolo, C. (2014) · Proceedings of the 12th ACM Conference on Embedded Network Sensor Systems · doi:10.1145/2668332.2668349 · Cited by 60
Self-citationMin, C., Lee, Y., Yoo, C., Kang, S., Choi, S., Park, P., Hwang, I., Ju, Y., Choi, S., & Song, J. (2015) · ACM Conference on Embedded Networked Sensor Systems (SenSys) · doi:10.1145/2809695.2809728 · Cited by 36
(2014) · doi:10.4230/oasics.slate.2021.16 · Cited by 1
Research works printed but not linked: 5
- zhizheng, 2015, Automatic Speaker Verification Spoofing and Countermeasures Challenge (ASVspoof 2015) Database, Centre for Speech Technology Research University of Edinburgh
- cplex, 2010, 12.2 User's Manual, IBM
- 10.1109/msp.2012.2205597 · DOI · Paper page
- bengio, 2015, Deep learning, MIT Press
- priyantha, 0, Enabling energy efficient continuous sensing on mobile nhones with littlerock, IPSN '10
Cited by
Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing
Zhou, Z., Chen, X., Li, E., Zeng, L., Luo, K., & Zhang, J. (2019) · Proceedings of the IEEE · doi:10.1109/jproc.2019.2918951 · Cited by 2,455
“Model Compression • Weight pruning and quantization to reduce storage and computation [70]–[77]”
BackgroundMethodInfluentialDeep Learning in Mobile and Wireless Networking: A Survey
Zhang, C., Patras, P., & Haddadi, H. (2019) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2019.2904897 · Cited by 1,768
Deep Learning With Edge Computing: A Review
Chen, J., & Ran, X. (2019) · Proceedings of the IEEE · doi:10.1109/jproc.2019.2921977 · Cited by 1,540
Federated Learning for Internet of Things: A Comprehensive Survey
Nguyen, D. C., Ding, M., Pathirana, P. N., Seneviratne, A., Li, J., & Vincent Poor, H. (2021) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2021.3075439 · Cited by 1,503
“The work in [205] introduces a software-based deep learning accelerator to support AI/DL training on mobile hardware.”
MethodConvergence of Edge Computing and Deep Learning: A Comprehensive Survey
Wang, X., Han, Y., Leung, V. C. M., Niyato, D., Yan, X., & Chen, X. (2020) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2020.2970550 · Cited by 1,498
“, GPUs, CPUs) on the end device [154], 2) distributed edge nodes [155], [156], or 3) collaborative “end-edge-cloud” architecture [12], [49], [157], [158].”
Background
Metadata
- Authors
- Lane, N. D., Bhattacharya, S., Georgiev, P., Forlivesi, C., Jiao, L., Qendro, L., & Kawsar, F.
- Affiliations
- Bell (Canada) (CA)
- University of Cambridge (GB)
- University of Bologna (IT)
- Venue
- 2016 15th ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN)
- Publisher
- IEEE
- Published
- 2016-04
- Pages
- 1-12
- OpenAlex
- W4236853429
- Cited by
- 450
- References
- 34
- Citations by year
- 2026: 47 · 2025: 40 · 2024: 30 · 2023: 39 · 2022: 55 · 2021: 62 · 2020: 74 · 2019: 52 · 2018: 32 · 2017: 15 · 2016: 4
- FWCI
- 26.45
- Type
- conference paper
- Language
- en
- Open access
- Locations
- ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN) (publishedVersion)
- Apollo (University of Cambridge) (submittedVersion)
- UCL Discovery (University College London) (submittedVersion)
- Apollo
- Topics
- Physical Sciences › Computer Science › Hardware and Architecture › Parallel Computing and Optimization Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Hardware and Architecture › Embedded Systems Design Techniques
- Keywords
- deep learning inference, mobile devices, low-power inference, model decomposition, heterogeneous processors, energy efficiency
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.