{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,28]],"date-time":"2026-10-28T17:13:00Z","timestamp":1793207580629,"version":"4.5.0"},"reference-count":172,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100000780","name":"European Commission","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3365349","type":"journal-article","created":{"date-parts":[[2024,2,12]],"date-time":"2024-02-12T14:35:28Z","timestamp":1707748528000},"page":"23406-23426","source":"Crossref","is-referenced-by-count":173,"title":["A Machine Learning-Oriented Survey on Tiny Machine Learning"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4941-2255","authenticated-orcid":false,"given":"Luigi","family":"Capogrosso","sequence":"first","affiliation":[{"name":"Department of Engineering for Innovation Medicine, University of Verona, Verona, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9619-9656","authenticated-orcid":false,"given":"Federico","family":"Cunico","sequence":"additional","affiliation":[{"name":"Department of Engineering for Innovation Medicine, University of Verona, Verona, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4177-1749","authenticated-orcid":false,"given":"Dong Seon","family":"Cheng","sequence":"additional","affiliation":[{"name":"Department of Engineering for Innovation Medicine, University of Verona, Verona, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4404-5791","authenticated-orcid":false,"given":"Franco","family":"Fummi","sequence":"additional","affiliation":[{"name":"Department of Engineering for Innovation Medicine, University of Verona, Verona, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0523-6042","authenticated-orcid":false,"given":"Marco","family":"Cristani","sequence":"additional","affiliation":[{"name":"Department of Engineering for Innovation Medicine, University of Verona, Verona, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.iot.2021.100461"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3390\/fi11040100"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.4236\/jcc.2015.35021"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2020.03.021"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/EEEIC.2016.7555867"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.rser.2015.12.114"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2021.08.006"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.17148\/IJARCCE.2016.56188"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3047960"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3034385"},{"key":"ref11","article-title":"Smart retail 4.0 IoT consumer retailer model for retail intelligence and strategic marketing of in-store products","volume-title":"Proc. 17th Int. Bus. Horizon-INBUSH ERA","volume":"9","author":"Jayaram"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2834151"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2983149"},{"issue":"1","key":"ref14","first-page":"28","article-title":"Smart factory for industry 4.0: A review","volume":"7","author":"Hozdi\u00e7","year":"2015","journal-title":"Int. J. Modern Manuf. Technol."},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/1541880.1541882"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JSYST.2019.2905565"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3390\/electronics8111289"},{"key":"ref18","first-page":"11711","article-title":"MCUNet: Tiny deep learning on IoT devices","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Lin"},{"key":"ref19","volume-title":"Tinyml: Machine Learning With Tensorflow Lite on Arduino and Ultra-Low-Power Microcontrollers","author":"Warden","year":"2019"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1002\/9781119785750.ch18"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21428\/bf6fb269.1f033948"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3583683"},{"key":"ref23","first-page":"11","article-title":"Automated HW\/SW co-design for edge AI: State, challenges and steps ahead","volume-title":"Proc. Int. Conf. Hardw.\/Softw. Codesign Syst. Synth.","author":"Bringmann"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3079209"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20044-1_41"},{"key":"ref26","article-title":"VeLO: Training versatile learned optimizers by scaling up","author":"Metz","year":"2022","journal-title":"arXiv:2211.09760"},{"key":"ref27","article-title":"Benchmarking TinyML systems: Challenges and direction","author":"Banbury","year":"2020","journal-title":"arXiv:2003.04821"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/MCAS.2020.3005467"},{"issue":"2","key":"ref29","first-page":"67","article-title":"Anomaly detection based on tiny machine learning: A review","volume":"9","author":"Siang","year":"2021","journal-title":"Open Int. J. Informat."},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3503823.3503836"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.jksuci.2021.11.019"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-08337-2_6"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/AICAS54282.2022.9870017"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/7437023"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.3390\/fi14120363"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3528227.3528569"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.3390\/mi13060851"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/3ICT56508.2022.9990661"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-022-10141-4"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2022.3210773"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS57527.2023.00024"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.3390\/info14020064"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3294111"},{"issue":"9","key":"ref44","first-page":"790","article-title":"The PRISMA 2020 statement: An updated guideline for reporting systematic reviews","volume-title":"Revista Espanola de Cardiologia English ed.","volume":"74","author":"Yepes-Nu\u00f1ez","year":"2021"},{"key":"ref45","volume-title":"Tinyml Design Contest","year":"2023"},{"key":"ref46","volume-title":"Tinyml Challenge 2022: Smart Weather Station","year":"2023"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN54540.2023.10191845"},{"key":"ref48","article-title":"Measuring what really matters: Optimizing neural networks for TinyML","author":"Heim","year":"2021","journal-title":"arXiv:2104.10645"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICTC.2018.8539530"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3447818.3460378"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/AICAS51828.2021.9458511"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICSICT49897.2020.9278154"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/SiPS.2014.6986099"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2019.0155"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICECS46596.2019.8965067"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2022.3198321"},{"key":"ref57","article-title":"Network trimming: A data-driven neuron pruning approach towards efficient deep architectures","author":"Hu","year":"2016","journal-title":"arXiv:1607.03250"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3005348"},{"key":"ref59","article-title":"To prune, or not to prune: Exploring the efficacy of pruning for model compression","author":"Zhu","year":"2017","journal-title":"arXiv:1710.01878"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3140659.3080215"},{"key":"ref61","article-title":"Rethinking the value of network pruning","author":"Liu","year":"2018","journal-title":"arXiv:1810.05270"},{"key":"ref62","first-page":"129","article-title":"What is the state of neural network pruning?","volume-title":"Proc. Mach. Learn. Syst.","volume":"2","author":"Blalock"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746843"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3182659"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3555776.3577747"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS46773.2023.10181746"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.574"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"ref69","article-title":"Quantizing deep convolutional networks for efficient inference: A whitepaper","author":"Krishnamoorthi","year":"2018","journal-title":"arXiv:1806.08342"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2019.00127"},{"key":"ref71","first-page":"7197","article-title":"Up or down? Adaptive rounding for post-training quantization","volume-title":"Proc. Int. Conf. Machine. Learn. (ICML)","author":"Nagel"},{"key":"ref72","first-page":"9847","article-title":"Towards accurate post-training network quantization via bit-split and stitching","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1201\/9781003162810-13"},{"key":"ref74","article-title":"Overcoming oscillations in quantization-aware training","author":"Nagel","year":"2022","journal-title":"arXiv:2203.11086"},{"key":"ref75","article-title":"An empirical study of low precision quantization for TinyML","author":"Zhuo","year":"2022","journal-title":"arXiv:2203.05492"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/AICAS57966.2023.10168657"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1145\/3591466"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.3390\/s23125696"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01389"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3007506"},{"key":"ref81","first-page":"1","article-title":"Improve object detection with feature-based knowledge distillation: Towards accurate and efficient detectors","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhang"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA52953.2021.00094"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC46164.2021.9630348"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107659"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-88004-0_9"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00775"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/IC2SPM56638.2022.9988992"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO55093.2022.9909572"},{"key":"ref90","first-page":"1","article-title":"Algorithms for hyper-parameter optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"24","author":"Bergstra"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.5555\/2188385.2188395"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.11989\/JEST.1674-862X.80904120"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CogMI52975.2021.00041"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_16"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19775-8_13"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1145\/3476995"},{"key":"ref97","first-page":"517","article-title":"MicroNets: Neural network architectures for deploying TinyML applications on commodity microcontrollers","volume-title":"Proc. Mach. Learn. Syst.","volume":"3","author":"Banbury"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1145\/3437984.3458836"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1145\/3447582"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.12.014"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3100554"},{"key":"ref102","article-title":"Data aware neural architecture search","author":"Njor","year":"2023","journal-title":"arXiv:2304.01821"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.3390\/chips2020008"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/PRIME58259.2023.10161736"},{"key":"ref105","article-title":"Pad\u00e9 activation units: End-to-end learning of flexible activation functions in deep networks","author":"Molina","year":"2019","journal-title":"arXiv:1907.06732"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.01.026"},{"key":"ref107","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017","journal-title":"arXiv:1704.04861"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-66"},{"key":"ref111","first-page":"1","article-title":"Attention-based models for speech recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Chorowski"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3019893"},{"key":"ref114","article-title":"AttendNets: Tiny deep image recognition neural networks for the edge via visual attention condensers","author":"Wong","year":"2020","journal-title":"arXiv:2009.14385"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3126456"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/COINS51742.2021.9524173"},{"key":"ref117","article-title":"MobileViT: Light-weight, general-purpose, and mobile-friendly vision transformer","author":"Mehta","year":"2021","journal-title":"arXiv:2110.02178"},{"key":"ref118","first-page":"12980","article-title":"Compress: Self-supervised learning by compressing representations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Abbasi Koohpayegani"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.3390\/s21041339"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1145\/3609425"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1145\/3606372"},{"key":"ref122","first-page":"3711","article-title":"DROCC: Deep robust one-class classification","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Goyal"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.3390\/s21144805"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1016\/j.iot.2021.100437"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/CSCI54926.2021.00159"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/MetroInd4.0IoT51437.2021.9488546"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.3390\/s22103838"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3090866"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3196049"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1007\/s11831-023-09884-2"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref132","article-title":"Resource efficient deep reinforcement learning for acutely constrained tinyml devices","volume-title":"Proc. Res. Symp. Tiny Mach. Learn.","author":"Svoboda"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557206"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3155162"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/ICCE56470.2023.10043558"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.07.129"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.3390\/s23042344"},{"key":"ref138","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3057046"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01098"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482378"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539467"},{"key":"ref143","article-title":"MetaLDC: Meta learning of low-dimensional computing classifiers for fast on-device adaption","author":"Liu","year":"2023","journal-title":"arXiv:2302.12347"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref145","first-page":"11285","article-title":"TinyTL: Reduce memory, not parameters for efficient on-device learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Cai"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533927"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2021.3121554"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1109\/SWC50871.2021.00023"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892356"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1145\/3604566"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref152","volume-title":"Machine Learning on Arm Cortex-m Microcontrollers","author":"Suda","year":"2019"},{"key":"ref153","article-title":"CMSIS-NN: Efficient neural network kernels for arm cortex-M CPUs","author":"Lai","year":"2018","journal-title":"arXiv:1801.06601"},{"key":"ref154","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"25","author":"Krizhevsky"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2018.00091"},{"key":"ref156","article-title":"Benchmarking TPU, GPU, and CPU platforms for deep learning","author":"Emma Wang","year":"2019","journal-title":"arXiv:1907.10701"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2890150"},{"issue":"4","key":"ref158","first-page":"3575","article-title":"Design and implementation of FPGA-based systems\u2014A review","volume":"3","author":"Sulaiman","year":"2009","journal-title":"Austral. J. Basic Appl. Sci."},{"key":"ref159","article-title":"A survey of FPGA based deep learning accelerators: Challenges and opportunities","author":"Wang","year":"2018","journal-title":"arXiv:1901.04988"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC55918.2022.00017"},{"key":"ref162","first-page":"800","article-title":"Tensorflow lite micro: Embedded machine learning for TinyML systems","volume-title":"Proc. Mach. Learn. Syst.","volume":"3","author":"David"},{"key":"ref163","volume-title":"Utensor: Tinyml Ai Inference Library","year":"2023"},{"key":"ref164","first-page":"1","article-title":"Edge impulse: An MLOPS platform for Tiny machine learning","volume-title":"Proc. Mach. Learn. Syst.","volume":"5","author":"Janapa Reddi"},{"key":"ref165","volume-title":"X-Cube-AI: AI Expansion Pack for STM32CUBEMX","year":"2023"},{"key":"ref166","volume-title":"Embedded Learning Library: An Open Source Library for Embedded Ai and Machine Learning From Microsoft","year":"2023"},{"key":"ref167","first-page":"578","article-title":"TVM: An automated end-to-end optimizing compiler for deep learning","volume-title":"Proc. 13th USENIX Symp. Operating Syst. Design Implement. (OSDI)","author":"Chen"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1145\/3589610.3596278"},{"key":"ref169","first-page":"336","article-title":"MLPerf training benchmark","volume":"2","author":"Mattson","year":"2020","journal-title":"Proc. Mach. Learn. Syst."},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00045"},{"key":"ref171","article-title":"MLPerf tiny benchmark","author":"Banbury","year":"2021","journal-title":"arXiv:2106.07597"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10380310\/10433185.pdf?arnumber=10433185","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T17:27:26Z","timestamp":1709227646000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10433185\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":172,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3365349","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}