{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T22:26:01Z","timestamp":1772749561345,"version":"3.50.1"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100014013","name":"U.K. Research and Innovation (UKRI) Centre for Doctoral Training in Machine Intelligence for Nano-Electronic Devices and Systems","doi-asserted-by":"publisher","award":["EP\/S024298\/1"],"award-info":[{"award-number":["EP\/S024298\/1"]}],"id":[{"id":"10.13039\/100014013","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council (EPSRC) International Centre for Spatial Computational Learning","doi-asserted-by":"publisher","award":["EP\/S030069\/1"],"award-info":[{"award-number":["EP\/S030069\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100016311","name":"ARM Ltd., Cambridge, U.K.","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100016311","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2024,4,1]]},"DOI":"10.1109\/jiot.2023.3331654","type":"journal-article","created":{"date-parts":[[2023,11,9]],"date-time":"2023-11-09T19:03:51Z","timestamp":1699556631000},"page":"11471-11479","source":"Crossref","is-referenced-by-count":6,"title":["Enabling ImageNet-Scale Deep Learning on MCUs for Accurate and Efficient Inference"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4959-4623","authenticated-orcid":false,"given":"Sulaiman","family":"Sadiq","sequence":"first","affiliation":[{"name":"Department of Electronics and Computer Science, University of Southampton, Southampton, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2921-4283","authenticated-orcid":false,"given":"Jonathon","family":"Hare","sequence":"additional","affiliation":[{"name":"Department of Electronics and Computer Science, University of Southampton, Southampton, U.K."}]},{"given":"Simon","family":"Craske","sequence":"additional","affiliation":[{"name":"Central Technology Group, ARM Ltd., Cambridge, U.K."}]},{"given":"Partha","family":"Maji","sequence":"additional","affiliation":[{"name":"Machine Learning Department, Tenstorrent, Cambridge, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4980-3894","authenticated-orcid":false,"given":"Geoff","family":"Merrett","sequence":"additional","affiliation":[{"name":"Department of Electronics and Computer Science, University of Southampton, Southampton, U.K."}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref2","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn. (PMLR)","author":"Tan"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref6","volume-title":"IoT connected devices worldwide 2019-2030","year":"2022"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2893866"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2805263"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2014.2306328"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.iot.2019.03.002"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2963635"},{"key":"ref12","article-title":"Machine learning model sizes and the parameter gap","author":"Villalobos","year":"2022","journal-title":"arXiv:2207.02852"},{"key":"ref13","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":"ref14","first-page":"1","article-title":"MicroNets: Neural network architectures for deploying tinyML applications on commodity microcontrollers","volume-title":"Proc. Mach. Learn. Syst.","volume":"3","author":"Banbury"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2020.2983648"},{"key":"ref16","first-page":"326","article-title":"Memory-driven mixed low precision quantization for enabling deep network inference on microcontrollers","volume-title":"Proc. Mach. Learn. Syst.","volume":"2","author":"Rusci"},{"key":"ref17","first-page":"2346","article-title":"Memory-efficient patch-based inference for tiny deep learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Lin"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00304"},{"key":"ref19","first-page":"1","article-title":"Binaryconnect: Training deep neural networks with binary weights during propagations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Courbariaux"},{"key":"ref20","first-page":"1","article-title":"Trained ternary quantization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhu"},{"issue":"1","key":"ref21","first-page":"6869","article-title":"Quantized neural networks: Training neural networks with low precision weights and activations","volume":"18","author":"Hubara","year":"2017","journal-title":"J. Mach. Learn. Res."},{"key":"ref22","first-page":"1","article-title":"And the bit goes down: Revisiting the quantization of neural networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Stock"},{"key":"ref23","first-page":"1","article-title":"Training with quantization noise for extreme model compression","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Fan"},{"key":"ref24","first-page":"598","article-title":"Optimal brain damage","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"LeCun"},{"key":"ref25","first-page":"1","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Han"},{"key":"ref26","first-page":"760","article-title":"Network pruning via transformable architecture search","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dong"},{"key":"ref27","first-page":"18456","article-title":"UDC: Unified DNAS for compressible TinyML models for neural processing units","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Fedorov"},{"key":"ref28","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017","journal-title":"arXiv:1704.04861"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01099"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00293"},{"key":"ref32","first-page":"1","article-title":"DEff-ARTS: Differentiable efficient architecture search","volume-title":"Proc. Adv. Neural Inf. Process. Syst., ML Syst. Workshop","author":"Sadiq"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3437984.3458836"},{"key":"ref34","first-page":"1","article-title":"TensorFlow lite micro: Embedded machine learning on TinyML systems","volume-title":"Proc. Mach. Learn. Syst.","volume":"3","author":"David"},{"key":"ref35","volume-title":"uTensor","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2021.3066883"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2976702"},{"key":"ref38","article-title":"CMSIS-NN: Efficient neural network kernels for arm cortex-M CPUs","author":"Lai","year":"2018","journal-title":"arXiv:1801.06601"},{"key":"ref39","first-page":"1","article-title":"ProxylessNAS: Direct neural architecture search on target task and hardware","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Cai"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3534594"},{"key":"ref42","article-title":"MLPerf tiny benchmark","author":"Banbury","year":"2021","journal-title":"arXiv:2106.07597"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6488907\/10479190\/10314415.pdf?arnumber=10314415","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,28]],"date-time":"2024-03-28T20:16:33Z","timestamp":1711656993000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10314415\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,1]]},"references-count":42,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2023.3331654","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"value":"2327-4662","type":"electronic"},{"value":"2372-2541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4,1]]}}}