{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T15:19:52Z","timestamp":1773415192718,"version":"3.50.1"},"reference-count":69,"publisher":"Association for Computing Machinery (ACM)","issue":"5s","license":[{"start":{"date-parts":[[2021,9,17]],"date-time":"2021-09-17T00:00:00Z","timestamp":1631836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100004663","name":"Ministry of Science and Technology, Taiwan","doi-asserted-by":"crossref","award":["MOST 110-2222-E-001-003-MY3"],"award-info":[{"award-number":["MOST 110-2222-E-001-003-MY3"]}],"id":[{"id":"10.13039\/501100004663","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Embed. Comput. Syst."],"published-print":{"date-parts":[[2021,10,31]]},"abstract":"<jats:p>\n            The increasing paradigm shift towards\n            <jats:italic>i<\/jats:italic>\n            ntermittent computing has made it possible to intermittently execute\n            <jats:italic>d<\/jats:italic>\n            eep neural network (DNN) inference on edge devices powered by ambient energy. Recently,\n            <jats:italic>n<\/jats:italic>\n            eural architecture search (NAS) techniques have achieved great success in automatically finding DNNs with high accuracy and low inference latency on the deployed hardware. We make a key observation, where NAS attempts to improve inference latency by primarily maximizing data reuse, but the derived solutions when deployed on intermittently-powered systems may be inefficient, such that the inference may not satisfy an end-to-end latency requirement and, more seriously, they may be unsafe given an insufficient energy budget. This work proposes iNAS, which introduces intermittent execution behavior into NAS to find accurate network architectures with corresponding execution designs, which can safely and efficiently execute under intermittent power. An intermittent-aware execution design explorer is presented, which finds the right balance between data reuse and the costs related to intermittent inference, and incorporates a preservation design search space into NAS, while ensuring the power-cycle energy budget is not exceeded. To assess an intermittent execution design, an intermittent-aware abstract performance model is presented, which formulates the key costs related to progress preservation and recovery during intermittent inference. We implement iNAS on top of an existing NAS framework and evaluate their respective solutions found for various datasets, energy budgets and latency requirements, on a Texas Instruments device. Compared to those NAS solutions that can safely complete the inference, the iNAS solutions reduce the intermittent inference latency by 60% on average while achieving comparable accuracy, with an average 7% increase in search overhead.\n          <\/jats:p>","DOI":"10.1145\/3476995","type":"journal-article","created":{"date-parts":[[2021,9,17]],"date-time":"2021-09-17T18:36:51Z","timestamp":1631903811000},"page":"1-27","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":34,"title":["Intermittent-Aware Neural Architecture Search"],"prefix":"10.1145","volume":"20","author":[{"given":"Hashan Roshantha","family":"Mendis","sequence":"first","affiliation":[{"name":"Academia Sinica, Taiwan"}]},{"given":"Chih-Kai","family":"Kang","sequence":"additional","affiliation":[{"name":"Academia Sinica and National Taiwan University, Taiwan"}]},{"given":"Pi-cheng","family":"Hsiu","sequence":"additional","affiliation":[{"name":"Academia Sinica, National Taiwan University and National Chi Nan University, Taiwan"}]}],"member":"320","published-online":{"date-parts":[[2021,9,17]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.5555\/3437539.3437731"},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3391893"},{"key":"e_1_2_1_3_1","volume-title":"State-of-charge estimation of supercapacitors in transiently-powered sensor nodes","author":"Ahn JunIck","year":"2021","unstructured":"JunIck Ahn , Daeyong Kim , Rhan Ha , and Hojung Cha . 2021. State-of-charge estimation of supercapacitors in transiently-powered sensor nodes . IEEE TCAD ( 2021 ). JunIck Ahn, Daeyong Kim, Rhan Ha, and Hojung Cha. 2021. State-of-charge estimation of supercapacitors in transiently-powered sensor nodes. IEEE TCAD (2021)."},{"key":"e_1_2_1_4_1","volume-title":"Reyes-Ortiz","author":"Anguita Davide","year":"2013","unstructured":"Davide Anguita , Alessandro Ghio , Luca Oneto , Xavier Parra , and Jorge L . Reyes-Ortiz . 2013 . Dataset for Human Activity Recognition using Smartphones . https:\/\/archive.ics.uci.edu\/ml\/datasets\/human+activity+recognition+using+smartphones. Davide Anguita, Alessandro Ghio, Luca Oneto, Xavier Parra, and Jorge L. Reyes-Ortiz. 2013. Dataset for Human Activity Recognition using Smartphones. https:\/\/archive.ics.uci.edu\/ml\/datasets\/human+activity+recognition+using+smartphones."},{"key":"e_1_2_1_5_1","unstructured":"ARM. 2021. Cortex M4 DSP ISA. https:\/\/developer.arm.com\/architectures\/instruction-sets\/dsp-extensions\/dsp-for-cortex-m.  ARM. 2021. Cortex M4 DSP ISA. https:\/\/developer.arm.com\/architectures\/instruction-sets\/dsp-extensions\/dsp-for-cortex-m."},{"key":"e_1_2_1_6_1","volume-title":"Max Lam, William Fu, Amin Fazel, Jeremy Holleman, Xinyuan Huang, Robert Hurtado, David Kanter, Anton Lokhmotov, et\u00a0al.","author":"Banbury Colby R.","year":"2020","unstructured":"Colby R. Banbury , Vijay Janapa Reddi , Max Lam, William Fu, Amin Fazel, Jeremy Holleman, Xinyuan Huang, Robert Hurtado, David Kanter, Anton Lokhmotov, et\u00a0al. 2020 . Benchmarking TinyML systems: Challenges and direction. arXiv preprint arXiv:2003.04821 (2020). Colby R. Banbury, Vijay Janapa Reddi, Max Lam, William Fu, Amin Fazel, Jeremy Holleman, Xinyuan Huang, Robert Hurtado, David Kanter, Anton Lokhmotov, et\u00a0al. 2020. Benchmarking TinyML systems: Challenges and direction. arXiv preprint arXiv:2003.04821 (2020)."},{"key":"e_1_2_1_7_1","volume-title":"Hamza Ouarnoughi, Smail Niar, Martin Wistuba, and Naigang Wang.","author":"Benmeziane Hadjer","year":"2021","unstructured":"Hadjer Benmeziane , Kaoutar El Maghraoui , Hamza Ouarnoughi, Smail Niar, Martin Wistuba, and Naigang Wang. 2021 . A comprehensive survey on hardware-aware neural architecture search. arXiv preprint arXiv:2101.09336 (2021). Hadjer Benmeziane, Kaoutar El Maghraoui, Hamza Ouarnoughi, Smail Niar, Martin Wistuba, and Naigang Wang. 2021. A comprehensive survey on hardware-aware neural architecture search. arXiv preprint arXiv:2101.09336 (2021)."},{"key":"e_1_2_1_8_1","volume-title":"Proc. of ICLR.","author":"Cai Han","year":"2019","unstructured":"Han Cai , Chuang Gan , Tianzhe Wang , Zhekai Zhang , and Song Han . 2019 . Once-for-all: Train one network and specialize it for efficient deployment . In Proc. of ICLR. Han Cai, Chuang Gan, Tianzhe Wang, Zhekai Zhang, and Song Han. 2019. Once-for-all: Train one network and specialize it for efficient deployment. In Proc. of ICLR."},{"key":"e_1_2_1_9_1","volume-title":"Proc. of ICLR.","author":"Cai Han","year":"2018","unstructured":"Han Cai , Ligeng Zhu , and Song Han . 2018 . ProxylessNAS: Direct neural architecture search on target task and hardware . In Proc. of ICLR. Han Cai, Ligeng Zhu, and Song Han. 2018. ProxylessNAS: Direct neural architecture search on target task and hardware. In Proc. of ICLR."},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2016.2616357"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3093337.3037711"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586121"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3296957.3173210"},{"key":"e_1_2_1_14_1","unstructured":"Cypress. 2019. Excelon LP 8-Mbit SPI F-RAM. https:\/\/www.cypress.com\/file\/444186\/download.  Cypress. 2019. Excelon LP 8-Mbit SPI F-RAM. https:\/\/www.cypress.com\/file\/444186\/download."},{"key":"e_1_2_1_15_1","volume-title":"Proc. of IEEE CVPR. 11398\u201311407","author":"Dai Xiaoliang","unstructured":"Xiaoliang Dai , Peizhao Zhang , Bichen Wu , Hongxu Yin , Fei Sun , Yanghan Wang , Marat Dukhan , Yunqing Hu , Yiming Wu , Yangqing Jia , : Towards efficient network design through platform-aware model adaptation . In Proc. of IEEE CVPR. 11398\u201311407 . Xiaoliang Dai, Peizhao Zhang, Bichen Wu, Hongxu Yin, Fei Sun, Yanghan Wang, Marat Dukhan, Yunqing Hu, Yiming Wu, Yangqing Jia, et al.2019. ChamNet: Towards efficient network design through platform-aware model adaptation. In Proc. of IEEE CVPR. 11398\u201311407."},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.5555\/3322706.3361996"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASAP.2018.8445101"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458473.3458822"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304011"},{"key":"e_1_2_1_20_1","volume-title":"Proc. of. IEEE\/ACM ICCAD. 1\u20137.","author":"Gong Chengyue","unstructured":"Chengyue Gong , Zixuan Jiang , Dilin Wang , Yibo Lin , Qiang Liu , and David Z. Pan . 2019. Mixed precision neural architecture search for energy efficient deep learning . In Proc. of. IEEE\/ACM ICCAD. 1\u20137. Chengyue Gong, Zixuan Jiang, Dilin Wang, Yibo Lin, Qiang Liu, and David Z. Pan. 2019. Mixed precision neural architecture search for energy efficient deep learning. In Proc. of. IEEE\/ACM ICCAD. 1\u20137."},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001163"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3316781.3317829"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299173"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3131672.3131699"},{"key":"e_1_2_1_25_1","unstructured":"Texas Instruments. 2014. EnergyTrace. http:\/\/www.ti.com\/tool\/ENERGYTRACE.  Texas Instruments. 2014. EnergyTrace. http:\/\/www.ti.com\/tool\/ENERGYTRACE."},{"key":"e_1_2_1_26_1","unstructured":"Texas Instruments. 2016. Low-energy Accelerator (LEA). http:\/\/www.ti.com\/lit\/an\/slaa720\/slaa720.pdf.  Texas Instruments. 2016. Low-energy Accelerator (LEA). http:\/\/www.ti.com\/lit\/an\/slaa720\/slaa720.pdf."},{"key":"e_1_2_1_27_1","unstructured":"Texas Instruments. 2018. MSP430FR5994 MCU. http:\/\/www.ti.com\/product\/MSP430FR5994.  Texas Instruments. 2018. MSP430FR5994 MCU. http:\/\/www.ti.com\/product\/MSP430FR5994."},{"key":"e_1_2_1_28_1","unstructured":"Maxim Integrated. 2021. MAX78000 Ultra-Low-Power MCU with Arm Cortex-M4 and a Convolutional Neural Network Accelerator. https:\/\/datasheets.maximintegrated.com\/en\/ds\/MAX78000.pdf.  Maxim Integrated. 2021. MAX78000 Ultra-Low-Power MCU with Arm Cortex-M4 and a Convolutional Neural Network Accelerator. https:\/\/datasheets.maximintegrated.com\/en\/ds\/MAX78000.pdf."},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/RTAS48715.2020.00-14"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411808"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/2983628"},{"key":"e_1_2_1_32_1","first-page":"4154","article-title":"Standing on the shoulders of giants: Hardware and neural architecture co-search with hot start","volume":"39","author":"Jiang Weiwen","year":"2020","unstructured":"Weiwen Jiang , Lei Yang , Sakyasingha Dasgupta , Jingtong Hu , and Yiyu Shi . 2020 . Standing on the shoulders of giants: Hardware and neural architecture co-search with hot start . IEEE TCAD 39 , 11 (2020), 4154 \u2013 4165 . Weiwen Jiang, Lei Yang, Sakyasingha Dasgupta, Jingtong Hu, and Yiyu Shi. 2020. Standing on the shoulders of giants: Hardware and neural architecture co-search with hot start. IEEE TCAD 39, 11 (2020), 4154\u20134165.","journal-title":"IEEE TCAD"},{"key":"e_1_2_1_33_1","first-page":"4805","article-title":"Hardware\/software co-exploration of neural architectures","volume":"39","author":"Jiang Weiwen","year":"2020","unstructured":"Weiwen Jiang , Lei Yang , Edwin Sha , Qingfeng Zhuge , Shouzhen Gu , Sakyasingha Dasgupta , Yiyu Shi , and Jingtong Hu . 2020 . Hardware\/software co-exploration of neural architectures . IEEE TCAD 39 , 12 (2020), 4805 \u2013 4815 . Weiwen Jiang, Lei Yang, Edwin Sha, Qingfeng Zhuge, Shouzhen Gu, Sakyasingha Dasgupta, Yiyu Shi, and Jingtong Hu. 2020. Hardware\/software co-exploration of neural architectures. IEEE TCAD 39, 12 (2020), 4805\u20134815.","journal-title":"IEEE TCAD"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3316781.3317757"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3218603.3218633"},{"key":"e_1_2_1_36_1","first-page":"3479","article-title":"Everything leaves footprints: Hardware accelerated intermittent deep inference","volume":"39","author":"Kang Chih-Kai","year":"2020","unstructured":"Chih-Kai Kang , Hashan Roshantha Mendis , Chun-Han Lin , Ming-Syan Chen , and Pi-Cheng Hsiu . 2020 . Everything leaves footprints: Hardware accelerated intermittent deep inference . IEEE TCAD 39 , 11 (2020), 3479 \u2013 3491 . Chih-Kai Kang, Hashan Roshantha Mendis, Chun-Han Lin, Ming-Syan Chen, and Pi-Cheng Hsiu. 2020. Everything leaves footprints: Hardware accelerated intermittent deep inference. IEEE TCAD 39, 11 (2020), 3479\u20133491.","journal-title":"IEEE TCAD"},{"key":"e_1_2_1_37_1","unstructured":"Kendryte. 2018. K210 AI Chip Datasheet. https:\/\/s3.cn-north-1.amazonaws.com.cn\/dl.kendryte.com\/documents\/kendryte_datasheet_20181011163248_en.pdf.  Kendryte. 2018. K210 AI Chip Datasheet. https:\/\/s3.cn-north-1.amazonaws.com.cn\/dl.kendryte.com\/documents\/kendryte_datasheet_20181011163248_en.pdf."},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3356250.3360030"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.23919\/DATE.2018.8342033"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.5555\/3437539.3437669"},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS51556.2021.9401799"},{"key":"e_1_2_1_43_1","volume-title":"An efficient hardware design for accelerating sparse cnns with NAS-based models","author":"Liang Yun","year":"2021","unstructured":"Yun Liang , Liqiang Lu , Yicheng Jin , Jiaming Xie , Ruirui Huang , Jiansong Zhang , and Wei Lin . 2021. An efficient hardware design for accelerating sparse cnns with NAS-based models . IEEE TCAD (Early access) ( 2021 ), 1\u20131. Yun Liang, Liqiang Lu, Yicheng Jin, Jiaming Xie, Ruirui Huang, Jiansong Zhang, and Wei Lin. 2021. An efficient hardware design for accelerating sparse cnns with NAS-based models. IEEE TCAD (Early access) (2021), 1\u20131."},{"key":"e_1_2_1_44_1","volume-title":"Proc. of NeurIPS.","author":"Lin Ji","year":"2020","unstructured":"Ji Lin , Wei-Ming Chen , Yujun Lin , John Cohn , Chuang Gan , and Song Han . 2020 . MCUNet: Tiny deep learning on IoT devices . In Proc. of NeurIPS. Ji Lin, Wei-Ming Chen, Yujun Lin, John Cohn, Chuang Gan, and Song Han. 2020. MCUNet: Tiny deep learning on IoT devices. In Proc. of NeurIPS."},{"key":"e_1_2_1_45_1","volume-title":"Proc. of ICLR.","author":"Liu Hanxiao","year":"2018","unstructured":"Hanxiao Liu , Karen Simonyan , Oriol Vinyals , Chrisantha Fernando , and Koray Kavukcuoglu . 2018 . Hierarchical representations for efficient architecture search . In Proc. of ICLR. Hanxiao Liu, Karen Simonyan, Oriol Vinyals, Chrisantha Fernando, and Koray Kavukcuoglu. 2018. Hierarchical representations for efficient architecture search. In Proc. of ICLR."},{"key":"e_1_2_1_46_1","volume-title":"Proc. of ICCAD. 1\u20138.","author":"Lu Qing","year":"2019","unstructured":"Qing Lu , Weiwen Jiang , Xiaowei Xu , Yiyu Shi , and Jingtong Hu . 2019 . On neural architecture search for resource-constrained hardware platforms . In Proc. of ICCAD. 1\u20138. Qing Lu, Weiwen Jiang, Xiaowei Xu, Yiyu Shi, and Jingtong Hu. 2019. On neural architecture search for resource-constrained hardware platforms. In Proc. of ICCAD. 1\u20138."},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2015.88"},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2015.7056060"},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2018.2815603"},{"key":"e_1_2_1_50_1","first-page":"1","article-title":"Alpaca: Intermittent execution without checkpoints","volume":"96","author":"Maeng Kiwan","year":"2017","unstructured":"Kiwan Maeng , Alexei Colin , and Brandon Lucia . 2017 . Alpaca: Intermittent execution without checkpoints . In Proc. of ACM OOPSLA. 96 : 1 \u2013 96 :30. Kiwan Maeng, Alexei Colin, and Brandon Lucia. 2017. Alpaca: Intermittent execution without checkpoints. In Proc. of ACM OOPSLA. 96:1\u201396:30.","journal-title":"Proc. of ACM OOPSLA."},{"key":"e_1_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3310273.3323435"},{"key":"e_1_2_1_52_1","unstructured":"Hashan Roshantha Mendis Chih-Kai Kang and Pi-Cheng Hsiu. 2021. iNAS Open Source Project. https:\/\/github.com\/EMCLab-Sinica\/Intermittent-aware-NAS.  Hashan Roshantha Mendis Chih-Kai Kang and Pi-Cheng Hsiu. 2021. iNAS Open Source Project. https:\/\/github.com\/EMCLab-Sinica\/Intermittent-aware-NAS."},{"key":"e_1_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11265-007-0085-2"},{"key":"e_1_2_1_54_1","volume-title":"6th International Conference on Learning Representations.","author":"Polino Antonio","year":"2018","unstructured":"Antonio Polino , Razvan Pascanu , and Dan-Adrian Alistarh . 2018 . Model compression via distillation and quantization . In 6th International Conference on Learning Representations. Antonio Polino, Razvan Pascanu, and Dan-Adrian Alistarh. 2018. Model compression via distillation and quantization. In 6th International Conference on Learning Representations."},{"key":"e_1_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3377930.3389834"},{"key":"e_1_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3140659.3080221"},{"key":"e_1_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3279755.3279759"},{"key":"e_1_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2761740"},{"key":"e_1_2_1_59_1","volume-title":"Le","author":"Tan Mingxing","year":"2019","unstructured":"Mingxing Tan , Bo Chen , Ruoming Pang , Vijay Vasudevan , Mark Sandler , Andrew Howard , and Quoc V . Le . 2019 . MnasNet: Platform-aware neural architecture search for mobile. In Proc. of IEEE CVPR. 2820\u20132828. Mingxing Tan, Bo Chen, Ruoming Pang, Vijay Vasudevan, Mark Sandler, Andrew Howard, and Quoc V. Le. 2019. MnasNet: Platform-aware neural architecture search for mobile. In Proc. of IEEE CVPR. 2820\u20132828."},{"key":"e_1_2_1_60_1","article-title":"A survey of techniques for intermittent computing","author":"Umesh Sumanth","year":"2020","unstructured":"Sumanth Umesh and Sparsh Mittal . 2020 . A survey of techniques for intermittent computing . Journal of Sys. Arch 112 (Aug 2020), 101859. Sumanth Umesh and Sparsh Mittal. 2020. A survey of techniques for intermittent computing. Journal of Sys. Arch 112 (Aug 2020), 101859.","journal-title":"Journal of Sys. Arch 112"},{"key":"e_1_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00215"},{"key":"e_1_2_1_62_1","volume-title":"Speech commands: A dataset for limited-vocabulary speech recognition. arXiv preprint arXiv:1804.03209","author":"Warden Pete","year":"2018","unstructured":"Pete Warden . 2018. Speech commands: A dataset for limited-vocabulary speech recognition. arXiv preprint arXiv:1804.03209 ( 2018 ). Pete Warden. 2018. Speech commands: A dataset for limited-vocabulary speech recognition. arXiv preprint arXiv:1804.03209 (2018)."},{"key":"e_1_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58526-6_39"},{"key":"e_1_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/1347375.1347389"},{"key":"e_1_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01099"},{"key":"e_1_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.5555\/3437539.3437702"},{"key":"e_1_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.5555\/3437539.3437784"},{"key":"e_1_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1145\/2684746.2689060"},{"key":"e_1_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1145\/3371392"},{"key":"e_1_2_1_70_1","volume-title":"Le","author":"Zoph Barret","year":"2017","unstructured":"Barret Zoph and Quoc V . Le . 2017 . Neural architecture search with reinforcement learning. In Proc. of ICLR. Barret Zoph and Quoc V. Le. 2017. Neural architecture search with reinforcement learning. In Proc. of ICLR."}],"container-title":["ACM Transactions on Embedded Computing Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3476995","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3476995","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:30:46Z","timestamp":1750188646000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3476995"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,17]]},"references-count":69,"journal-issue":{"issue":"5s","published-print":{"date-parts":[[2021,10,31]]}},"alternative-id":["10.1145\/3476995"],"URL":"https:\/\/doi.org\/10.1145\/3476995","relation":{},"ISSN":["1539-9087","1558-3465"],"issn-type":[{"value":"1539-9087","type":"print"},{"value":"1558-3465","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,9,17]]},"assertion":[{"value":"2021-04-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-07-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-09-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}