The DOI matches its Crossref record; 8 of the 8 references it cites were found in a registry or an index.
Intelligence Beyond the Edge: Inference on Intermittent Embedded Systems
Open accessAbstract
Energy-harvesting technology provides a promising platform for future IoT applications. However, since communication is very expensive in these devices, applications will require inference "beyond the edge" to avoid wasting precious energy on pointless communication. We show that application performance is highly sensitive to inference accuracy. Unfortunately, accurate inference requires large amounts of computation and memory, and energy-harvesting systems are severely resource-constrained. Moreover, energy-harvesting systems operate intermittently, suffering frequent power failures that corrupt results and impede forward progress. This paper overcomes these challenges to present the first full-scale demonstration of DNN inference on an energy-harvesting system. We design and implement SONIC, an intermittence-aware software system with specialized support for DNN inference. SONIC introduces loop continuation, a new technique that dramatically reduces the cost of guaranteeing correct intermittent execution for loop-heavy code like DNN inference. To build a complete system, we further present GENESIS, a tool that automatically compresses networks to optimally balance inference accuracy and energy, and TAILS, which exploits SIMD hardware available in some microcontrollers to improve energy efficiency. Both SONIC & TAILS guarantee correct intermittent execution without any hand-tuning or performance loss across different power systems. Across three neural networks on a commercially available microcontroller, SONIC & TAILS reduce inference energy by 6.9× and 12.2×, respectively, over the state-of-the-art.
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.
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
Xception: Deep Learning with Depthwise Separable Convolutions
Chollet, F. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.195 · Cited by 20,380
Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
Szegedy, C., Ioffe, S., Vanhoucke, V., & Alemi, A. (2017) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v31i1.11231 · Cited by 4,636
Eyeriss: a spatial architecture for energy-efficient dataflow for convolutional neural networks
Chen, Y.-H., Emer, J., & Sze, V. (2016) · ACM SIGARCH Computer Architecture News · doi:10.1145/3007787.3001177 · Cited by 1,182
EIE: Efficient Inference Engine on Compressed Deep Neural Network
Han, S., Liu, X., Mao, H., Pu, J., Pedram, A., Horowitz, M. A., & Dally, W. J. (2016) · 2016 ACM/IEEE 43rd Annual International Symposium on Computer Architecture (ISCA) · doi:10.1109/isca.2016.30 · Cited by 1,077
Alwani, M., Chen, H., Ferdman, M., & Milder, P. (2016) · 2016 49th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO) · doi:10.1109/micro.2016.7783725 · Cited by 662
Handwritten digit recognition: applications of neural network chips and automatic learning
Le Cun, Y., Jackel, L. D., Boser, B., Denker, J. S., Graf, H. P., Guyon, I., Henderson, D., Howard, R. E., & Hubbard, W. (1989) · IEEE Communications Magazine · doi:10.1109/35.41400 · Cited by 480 · cited 2×
“llelism to ensure correctness with intermittent power. We evaluate SONIC & TAILS on a TI MSP430 microcontroller [2] using an RF-energy harvester [4, 5] (Secs. 8 & 9). On three real-world DNNs [42, 48, 69], SONIC improves inference efficiency by6.9× on average over Alpaca [54], a state-of-the-art intermittent s…”
BackgroundMethodInfluential
Research works printed but not linked: 67
- 10.1109/ISCA.2016.11 · DOI · Paper page
- 10.5555/3195638.3195664 · doi:10.5555/3195638.3195664
- 10.1145/2994551.2994564 · DOI · Paper page
- 10.5555/1972457.1972478 · doi:10.5555/1972457.1972478
- 10.1145/2541940.2541967 · DOI · Paper page
- 10.1109/MICRO.2014.58 · DOI · Paper page
- 10.1109/ISCA.2016.40 · DOI · Paper page
- 10.1145/2872362.2872409 · doi:10.1145/2872362.2872409
- 10.1145/2983990.2983995 · DOI · Paper page
- Alexei Colin Emily Ruppel and Brandon Lucia. 2018. A Reconfigurable Energy Storage Architecture for Energy-harvesting Devices. In ASPLOS . 10.1145/3173162.3173210 · doi:10.1145/3173162.3173210
- Matthieu Courbariaux, Itay Hubara, Daniel Soudry, Ran El-Yaniv, and Yoshua Bengio. 2016. Binarized neural networks: Training deep neural networks with weights and activations constrained to +1 or-1. arXiv preprint arXiv:1602.02830 (2016). · arXiv
- 10.1145/633625.52417 · doi:10.1145/633625.52417
- 10.1109/MC.2008.224 · doi:10.1109/mc.2008.224
- 10.1137/S0895479896305696 · DOI · Paper page
- 10.1137/S0895479898346995 · DOI · Paper page
- 10.1145/3079856.3080248 · DOI
- 10.1145/3123939.3124552 · DOI · Paper page
- 10.1109/PERCOMW.2017.7917625 · DOI
- 10.1145/2749469.2750389 · DOI · Paper page
- 10.1109/PACT.2017.58 · DOI
- L. Fick, D. Blaauw, D. Sylvester, S. Skrzyniarz, M. Parikh, and D. Fick. 2017. Analog in-memory subthreshold deep neural network accelerator. In 2017 IEEE Custom Integrated Circuits Conference (CICC). 1--4.
- 10.1145/3097983.3098043 · DOI · Paper page
- 10.1109/MM.2012.51 · doi:10.1109/mm.2012.51
- 10.5555/3305381.3305519 · doi:10.5555/3305381.3305519
- 10.1145/1816038.1815968 · DOI
- Song Han, Huizi Mao, and William J. Dally. 2016b. Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization, and Huffman Coding. In Proc. of the 5th Intl. Conf. on Learning Representationas (Proc. ICLR'16) .
- 10.1145/2994551.2994554 · DOI
- 10.1145/2809695.2809707 · doi:10.1145/2809695.2809707
- 10.1145/3131672.3131674 · DOI
- 10.1145/3131672.3131673 · doi:10.1145/3131672.3131673
- 10.1145/3079856.3080238 · doi:10.1145/3079856.3080238
- 10.1109/ISSCC.2014.6757323 · DOI · Paper page
- Sergey Ioffe and Christian Szegedy. 2015. Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167 (2015). · arXiv
- H. Jayakumar A. Raha and V. Raghunathan. 2014. QuickRecall: A Low Overhead HW/SW Approach for Enabling Computations across Power Cycles in Transiently Powered Computers. In Int'l Conf. on VLSI Design and Int'l Conf. on Embedded Systems . 10.1109/VLSID.2014.63 · doi:10.1109/vlsid.2014.63
- Norman P Jouppi, Cliff Young, Nishant Patil, David Patterson, Gaurav Agrawal, Raminder Bajwa, Sarah Bates, Suresh Bhatia, Nan Boden, Al Borchers, et almbox. 2017. In-datacenter performance analysis of a tensor processing unit. arXiv preprint arXiv:1704.04760 (2017). · arXiv
- 10.1145/3173162.3173176 · DOI · Paper page
- 10.1145/2737924.2737978 · DOI
- 10.1145/3123939.3124533 · doi:10.1145/3123939.3124533
- 10.1109/HPCA.2015.7056060 · DOI · Paper page
- 10.1145/3133920 · DOI · Paper page
- 10.5555/3291168.3291178 · doi:10.5555/3291168.3291178
- 10.1109/LCA.2017.2777834 · doi:10.1109/lca.2017.2777834
- A. Mirhoseini, E. M. Songhori, and F. Koushanfar. 2013. Idetic: A High-level Synthesis Approach for Enabling Long Computations on Transiently-powered ASICs. In IEEE Pervasive Computing and Communication Conference (PerCom). http://aceslab.org/sites/default/files/Idetic.pdf
- 10.5555/541177 · doi:10.5555/541177
- 10.5555/3291168.3291210 · doi:10.5555/3291168.3291210
- 10.1016/0893-6080(94)90058-2 · DOI
- 10.1145/2996884.2996888 · DOI
- Preetum Nakkiran, Raziel Alvarez, Rohit Prabhavalkar, and Carolina Parada. 2015. Compressing deep neural networks using a rank-constrained topology.. In Sixteenth Annual Conference of the International Speech Communication Association .
- 10.1145/2749469.2750380 · DOI
- 10.1145/3079856.3080254 · DOI · Paper page
- 10.1145/3079856.3080256 · DOI · Paper page
- 10.1109/JSSC.2017.2752838 · DOI
- 10.1145/1950365.1950386 · doi:10.1145/1950365.1950386
- 10.1145/3037697.3037746 · DOI
- Tara N Sainath and Carolina Parada. 2015. Convolutional neural networks for small-footprint keyword spotting. In 16th Annual Conference of the International Speech Communication Association .
- 10.1109/TIM.2008.925019 · DOI · Paper page
- 10.1145/859618.859667 · doi:10.1145/859618.859667
- Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014). · arXiv
- M. Song, K. Zhong, J. Zhang, Y. Hu, D. Liu, W. Zhang, J. Wang, and T. Li. 2018. In-Situ AI: Towards Autonomous and Incremental Deep Learning for IoT Systems. In 2018 IEEE International Symposium on High Performance Computer Architecture (HPCA). 92--103.
- 10.5555/3298023.3298188 · doi:10.5555/3298023.3298188
- 10.1109/CVPR.2015.7298594 · DOI · Paper page
- Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, Andrew Rabinovich, et almbox. 2015b. Going deeper with convolutions. Cvpr.
- 10.1109/CVPR.2016.308 · DOI · Paper page
- TI Inc. 2014. Overview for MSP430FRxx FRAM. http://ti.com/wolverine. Visited July 28, 2014.
- 10.1007/BF02289464 · DOI · Paper page
- 10.5555/3026877.3026880 · doi:10.5555/3026877.3026880
- 10.5555/3195638.3195662 · doi:10.5555/3195638.3195662
Cited by
Collaborative Federated Learning for Healthcare: Multi-Modal COVID-19 Diagnosis at the Edge
Qayyum, A., Ahmad, K., Ahsan, M. A., Al-Fuqaha, A., & Qadir, J. (2022) · IEEE Open Journal of the Computer Society · doi:10.1109/ojcs.2022.3206407 · Cited by 345
“…predicting unseen objects/classes based on the previous knowledge/trained data, help the IoTs to perform different activities, such as cancer prognosis, brain tumor classification, and other clinical data analysis at the edge devices resulting in reduced latency and bandwidth in telemedicine [35].”
BackgroundOrbital Edge Computing: Nanosatellite Constellations as a New Class of Computer System
Denby, B., & Lucia, B. (2020) · Proceedings of the Twenty-Fifth International Conference on Architectural Support for Programming Languages and Operating Systems · doi:10.1145/3373376.3378473 · Cited by 273
Self-citationMachine Learning for Microcontroller-Class Hardware: A Review
Saha, S. S., Sandha, S. S., & Srivastava, M. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3210773 · Cited by 253
Bringing ai to edge: from deep learning’s perspective
Liu, D., Kong, H., Luo, X., Liu, W., & Subramaniam, R. (2022) · Neurocomputing · doi:10.1016/j.neucom.2021.04.141 · Cited by 171
“Especially, in future edge era, more and more customized DNN models for specific tasks will be developed and implemented on different hardware platforms, e.g., edge systems with intermittent power supply [169].”
BackgroundEnabling Large Neural Networks on Tiny Microcontrollers with Swapping
Miao, H., & Lin, F. X. (2021) · arXiv · doi:10.48550/arxiv.2101.08744 · Cited by 12
Metadata
- Authors
- Gobieski, G., Lucia, B., & Beckmann, N.
- Venue
- Proceedings of the Twenty-Fourth International Conference on Architectural Support for Programming Languages and Operating Systems
- Publisher
- ACM
- Published
- 2019-04-04
- Pages
- 199-213
- OpenAlex
- W2897303255
- Cited by
- 203
- References
- 8
- FWCI
- 24.47
- Type
- conference paper
- Language
- en
- Open access
- bronze
- Funders
- National Science Foundation (CCF-1815882,CCF-1751029)
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Intelligence Beyond the Edge: Inference on Intermittent Embedded Systems. https://app.cochat.ai/papers/10.1145/3297858.3304011
- The paper
- Gobieski, G., Lucia, B., & Beckmann, N. (2019). Intelligence Beyond the Edge: Inference on Intermittent Embedded Systems. Proceedings of the Twenty-Fourth International Conference on Architectural Support for Programming Languages and Operating Systems. https://doi.org/10.1145/3297858.3304011
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.