{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:13:44Z","timestamp":1719706424724},"reference-count":30,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"12","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Electron. Express"],"published-print":{"date-parts":[[2024,6,25]]},"DOI":"10.1587\/elex.21.20240206","type":"journal-article","created":{"date-parts":[[2024,5,9]],"date-time":"2024-05-09T22:13:30Z","timestamp":1715292810000},"page":"20240206-20240206","source":"Crossref","is-referenced-by-count":0,"title":["Advancing energy efficiency of spiking neural network accelerator via dynamic predictive early stopping"],"prefix":"10.1587","volume":"21","author":[{"given":"Yijie","family":"Miao","sequence":"first","affiliation":[{"name":"Dept. of Electrical Engineering and Information Systems, The University of Tokyo"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Makoto","family":"Ikeda","sequence":"additional","affiliation":[{"name":"Dept. of Electrical Engineering and Information Systems, The University of Tokyo"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"crossref","unstructured":"[1] K. Roy, <i>et al.<\/i>: \u201cTowards spike-based machine intelligence with neuromorphic computing,\u201d Nature <b>575<\/b> (2019) 607 (DOI: 10.1038\/s41586-019-1677-2).","DOI":"10.1038\/s41586-019-1677-2"},{"key":"2","doi-asserted-by":"crossref","unstructured":"[2] M. Osswald, <i>et al.<\/i>: \u201cA spiking neural network model of 3D perception for event-based neuromorphic stereo vision systems,\u201d Sci. Rep. <b>7<\/b> (2017) 40703 (DOI: 10.1038\/srep40703).","DOI":"10.1038\/srep40703"},{"key":"3","doi-asserted-by":"crossref","unstructured":"[3] M. Yao, <i>et al.<\/i>: \u201cTemporal-wise attention spiking neural networks for event streams classification,\u201d IEEE\/CVF International Conference on Computer Vision (2021) 10201 (DOI: 10.1109\/ICCV48922.2021.01006).","DOI":"10.1109\/ICCV48922.2021.01006"},{"key":"4","doi-asserted-by":"crossref","unstructured":"[4] Y. Cao, <i>et al.<\/i>: \u201cSpiking deep convolutional neural networks for energy-efficient object recognition,\u201d Int. J. Comput. Vis. <b>113<\/b> (2015) 54 (DOI: 110.1007\/s11263-014-0788-3).","DOI":"10.1007\/s11263-014-0788-3"},{"key":"5","unstructured":"[5] B. Rueckauer, <i>et al.<\/i>: \u201cA spiking neural network model of 3D perception for event-based neuromorphic stereo vision systems,\u201d Frontiers in Neuroscience <b>11<\/b> (2017) 682 (DOI: 10.3389\/fnins.2017.00682)."},{"key":"6","doi-asserted-by":"crossref","unstructured":"[6] A. Sengupta, <i>et al.<\/i>: \u201cGoing deeper in spiking neural networks: VGG and residual architectures,\u201d arXiv preprint (2018) arXiv: 1802.02627 (DOI: 10.48550\/arXiv.1802.02627).","DOI":"10.3389\/fnins.2019.00095"},{"key":"7","unstructured":"[7] S.B. Shrestha, <i>et al.<\/i>: \u201cSLAYER: spike layer error reassignment in time,\u201d arXiv preprint (2018) arXiv: 1810.08646 (DOI: 10.48550\/arXiv.1810.08646)."},{"key":"8","doi-asserted-by":"crossref","unstructured":"[8] Q. Fu and H. Dong: \u201cAn ensemble unsupervised spiking neural network for objective recognition,\u201d Neurocomputing <b>419<\/b> (2021) 47 (DOI: 10.1016\/j.neucom.2020.07.109).","DOI":"10.1016\/j.neucom.2020.07.109"},{"key":"9","doi-asserted-by":"crossref","unstructured":"[9] S. Hwang, <i>et al.<\/i>: \u201cLow-latency spiking neural networks using pre-charged membrane potential and delayed evaluation,\u201d Frontiers in Neuroscience <b>15<\/b> (2021) 629000 (DOI: 10.3389\/fnins.2021.629000).","DOI":"10.3389\/fnins.2021.629000"},{"key":"10","doi-asserted-by":"crossref","unstructured":"[10] D. Neil and S.-C. Liu: \u201cMinitaur, an event-driven FPGA-based spiking network accelerator,\u201d IEEE Trans. Very Large Scale Integr. (VLSI) Syst. <b>22<\/b> (2014) 2621 (DOI: 10.1109\/TVLSI.2013.2294916).","DOI":"10.1109\/TVLSI.2013.2294916"},{"key":"11","doi-asserted-by":"crossref","unstructured":"[11] J. Zhang, <i>et al.<\/i>: \u201cAn asynchronous reconfigurable SNN accelerator with event-driven time step update,\u201d IEEE Asian Solid-State Circuits Conference (2019) 213 (DOI: 10.1109\/A-SSCC47793.2019.9056903).","DOI":"10.1109\/A-SSCC47793.2019.9056903"},{"key":"12","doi-asserted-by":"crossref","unstructured":"[12] X. Ju, <i>et al.<\/i>: \u201cAn FPGA implementation of deep spiking neural networks for low-power and fast classification,\u201d Neural Comput. <b>32<\/b> (2020) 182 (DOI: 10.1162\/neco_a_01245).","DOI":"10.1162\/neco_a_01245"},{"key":"13","doi-asserted-by":"crossref","unstructured":"[13] D. Gerlinghoff, <i>et al.<\/i>: \u201cE3NE: an end-to-end framework for accelerating spiking neural networks with emerging neural encoding on FPGAs,\u201d IEEE Trans. Parallel Distrib. Syst. <b>33<\/b> (2022) 3207 (DOI: 10.1109\/TPDS.2021.3128945).","DOI":"10.1109\/TPDS.2021.3128945"},{"key":"14","doi-asserted-by":"crossref","unstructured":"[14] S. Panchapakesan, <i>et al.<\/i>: \u2018SyncNN: evaluating and accelerating spiking neural networks on FPGAs,\u201d ACM Trans. Reconfigurable Technol. Syst. <b>15<\/b> (2022) 1 (DOI: 10.1145\/3514253).","DOI":"10.1145\/3514253"},{"key":"15","doi-asserted-by":"crossref","unstructured":"[15] J. Li, <i>et al.<\/i>: \u201cFireFly: a high-throughput hardware accelerator for spiking neural networks with efficient DSP and memory optimization,\u201d IEEE Trans. Very Large Scale Integr. (VLSI) Syst. <b>31<\/b> (2023) 1178 (DOI: 10.1109\/TVLSI.2023.3279349).","DOI":"10.1109\/TVLSI.2023.3279349"},{"key":"16","doi-asserted-by":"crossref","unstructured":"[16] Y. Liang, <i>et al.<\/i>: \u201cEvaluating fast algorithms for convolutional neural networks on FPGAs,\u201d IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst. <b>39<\/b> (2020) 857 (DOI: 10.1109\/TCAD.2019.2897701).","DOI":"10.1109\/TCAD.2019.2897701"},{"key":"17","doi-asserted-by":"crossref","unstructured":"[17] L. Xuan, <i>et al.<\/i>: \u201cAn FPGA-based energy-efficient reconfigurable depthwise separable convolution accelerator for image recognition,\u201d IEEE Trans. Circuits Syst. II, Exp. Briefs <b>69<\/b> (2022) 4003 (DOI: 10.1109\/TCSII.2022.3180553).","DOI":"10.1109\/TCSII.2022.3180553"},{"key":"18","doi-asserted-by":"crossref","unstructured":"[18] Z. Li, <i>et al.<\/i>: \u201cHBCA: a toolchain for high-accuracy branch-fused CNN accelerator on FPGA with dual-decimal-fused technique,\u201d Electronics <b>12<\/b> (2023) 192 (DOI: 10.3390\/electronics12010192).","DOI":"10.3390\/electronics12010192"},{"key":"19","doi-asserted-by":"crossref","unstructured":"[19] A. Javanshir, <i>et al.<\/i>: \u201cAdvancements in algorithms and neuromorphic hardware for spiking neural networks,\u201d Neural Computation <b>34<\/b> (2022) 1289 (DOI: 10.1162\/neco_a_01499).","DOI":"10.1162\/neco_a_01499"},{"key":"20","unstructured":"[20] Z. Wang, <i>et al.<\/i>: \u201cTowards lossless ANN-SNN conversion under ultra-low latency with dual-phase optimization,\u201d arXiv preprint (2022) arXiv: 2205.07473 (DOI: 10.48550\/arXiv.2205.07473)."},{"key":"21","unstructured":"[21] K. Simonyan and A. Zisserman: \u201cVery deep convolutional networks for large-scale image recognition,\u201d arXiv preprint (2014) arXiv: 1409.1556 (DOI: 10.48550\/arXiv.1409.1556)."},{"key":"22","unstructured":"[22] A. Krizhevsky: \u201cLearning Multiple Layers of Features from Tiny Images,\u201d (2009) https:\/\/www.cs.toronto.edu\/~kriz\/learning-features-2009-TR.pdf."},{"key":"23","doi-asserted-by":"crossref","unstructured":"[23] Y. Miao and M. Ikeda: \u201cLossless method of constraining membrane potential in deep spiking neural networks,\u201d Artificial Intelligence Applications and Innovations (2023) 529 (DOI: 10.1007\/978-3-031-34107-6_42).","DOI":"10.1007\/978-3-031-34107-6_42"},{"key":"24","doi-asserted-by":"crossref","unstructured":"[24] J. Kim, <i>et al.<\/i>: \u201cDeep neural networks with weighted spikes,\u201d Neurocomputing <b>311<\/b> (2018) 373 (DOI: 10.1016\/j.neucom.2018.05.087).","DOI":"10.1016\/j.neucom.2018.05.087"},{"key":"25","doi-asserted-by":"crossref","unstructured":"[25] J.E. Smith: \u201cA study of branch prediction strategies,\u201d 25 Years of the International Symposia on Computer Architecture (1998) 202 (DOI: 10.1145\/285930.285980).","DOI":"10.1145\/285930.285980"},{"key":"26","doi-asserted-by":"crossref","unstructured":"[26] M. Alwani, <i>et al.<\/i>: \u201cFused-layer CNN accelerators,\u201d IEEE\/ACM International Symposium on Microarchitecture (2016) 1 (DOI: 10.1109\/MICRO.2016.7783725).","DOI":"10.1109\/MICRO.2016.7783725"},{"key":"27","doi-asserted-by":"crossref","unstructured":"[27] L. Zhang, <i>et al<\/i>.: \u201cA cost-efficient high-speed VLSI architecture for spiking convolutional neural network inference using time-step binary spike maps,\u201d Sensors <b>21<\/b> (2021) 6006 (DOI: 10.3390\/s21186006).","DOI":"10.3390\/s21186006"},{"key":"28","unstructured":"[28] Y. He, <i>et al.<\/i>: \u201cChannel pruning for accelerating very deep neural networks,\u201d arXiv preprint (2017) arXiv: 1707.06168 (DOI: 10.48550\/arXiv.1707.06168)."},{"key":"29","doi-asserted-by":"crossref","unstructured":"[29] J.-W. Jang, <i>et al.<\/i>: \u201cSparsity-aware and re-configurable NPU architecture for Samsung flagship mobile SoC,\u201d ACM\/IEEE 48th Annual International Symposium on Computer Architecture (ISCA) (2021) 15 (DOI: 10.1109\/ISCA52012.2021.00011).","DOI":"10.1109\/ISCA52012.2021.00011"},{"key":"30","unstructured":"[30] R. Yin, <i>et al.<\/i>: \u201cSATA: sparsity-aware training accelerator for spiking neural networks,\u201d arXiv preprint (2022) arXiv: 2204.05422 (DOI: 10.48550\/arXiv.2204.05422)."}],"container-title":["IEICE Electronics Express"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/elex\/21\/12\/21_21.20240206\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,29]],"date-time":"2024-06-29T03:29:21Z","timestamp":1719631761000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/elex\/21\/12\/21_21.20240206\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,25]]},"references-count":30,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2024]]}},"URL":"https:\/\/doi.org\/10.1587\/elex.21.20240206","relation":{},"ISSN":["1349-2543"],"issn-type":[{"value":"1349-2543","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6,25]]},"article-number":"21.20240206"}}