{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T14:51:55Z","timestamp":1776783115305,"version":"3.51.2"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100014438","name":"Industrial Machine Learning for Enterprises (IML4E) Project of ITEA4 funded by Business Finland","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100014438","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3275431","type":"journal-article","created":{"date-parts":[[2023,5,11]],"date-time":"2023-05-11T17:38:05Z","timestamp":1683826685000},"page":"90158-90180","source":"Crossref","is-referenced-by-count":16,"title":["Systematic Literature Review on Cost-Efficient Deep Learning"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6578-6284","authenticated-orcid":false,"given":"Antti","family":"Klemetti","sequence":"first","affiliation":[{"name":"Department of Computer Science, Faculty of Science, University of Helsinki, Helsinki, Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2410-0722","authenticated-orcid":false,"given":"Mikko","family":"Raatikainen","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Faculty of Science, University of Helsinki, Helsinki, Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0953-9825","authenticated-orcid":false,"given":"Lalli","family":"Myllyaho","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Faculty of Science, University of Helsinki, Helsinki, Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8540-9918","authenticated-orcid":false,"given":"Tommi","family":"Mikkonen","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology, University of Jyväskylä, Jyväskylä, Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5083-1927","authenticated-orcid":false,"given":"Jukka K.","family":"Nurminen","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Faculty of Science, University of Helsinki, Helsinki, Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3337821.3337873"},{"key":"ref12","article-title":"Large scale distributed deep networks","volume":"25","author":"dean","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref14","article-title":"Guidelines for performing systematic literature reviews in software engineering","author":"kitchenham","year":"2007"},{"key":"ref53","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449854"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2018.2876857"},{"key":"ref55","article-title":"An overview of gradient descent optimization algorithms","author":"ruder","year":"2016","journal-title":"arXiv 1609 04747"},{"key":"ref10","article-title":"Deep learning scaling is predictable, empirically","author":"hestness","year":"2017","journal-title":"arXiv 1712 00409"},{"key":"ref54","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2017","journal-title":"arXiv 1711 05101"},{"key":"ref17","article-title":"Semi-supervised classification with graph convolutional networks","author":"kipf","year":"2017","journal-title":"arXiv 1609 02907"},{"key":"ref16","article-title":"Generative adversarial nets","volume":"27","author":"goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2019.07.007"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3381831"},{"key":"ref51","year":"2022","journal-title":"PyTorch"},{"key":"ref50","year":"2022","journal-title":"TensorFlow"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3282307"},{"key":"ref45","first-page":"800","article-title":"Tensorflow lite micro: Embedded machine learning for TinyML systems","volume":"3","author":"david","year":"2021","journal-title":"Proc Mach Learn Syst"},{"key":"ref48","year":"2022","journal-title":"Apple Core ML"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1080\/23746149.2016.1259585"},{"key":"ref42","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017","journal-title":"arXiv 1704 04861"},{"key":"ref41","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2015","journal-title":"Proc NIPS DEEP Learn Workshop"},{"key":"ref44","year":"2022","journal-title":"ML for Mobile and Edge Devices"},{"key":"ref43","first-page":"1157","article-title":"An introduction to variable and feature selection","volume":"3","author":"guyon","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref49","year":"2022","journal-title":"Android ML"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/216585.216588"},{"key":"ref7","first-page":"10","article-title":"1.1 computing’s energy problem (and what we can do about it)","author":"horowitz","year":"2014","journal-title":"IEEE Int Solid-State Circuits Conf (ISSCC) Dig Tech Papers"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2019.00048"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2342509.2342513"},{"key":"ref6","article-title":"ImageNet classification with deep convolutional neural networks","volume":"25","author":"krizhevsky","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00059"},{"key":"ref40","article-title":"Do deep nets really need to be deep?","volume":"27","author":"ba","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref35","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","author":"han","year":"2015","journal-title":"arXiv 1510 00149 [cs]"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.infsof.2010.03.014"},{"key":"ref37","article-title":"BinaryConnect: Training deep neural networks with binary weights during propagations","volume":"28","author":"courbariaux","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref36","article-title":"Pruning filters for efficient ConvNets","author":"li","year":"2016","journal-title":"arXiv 1608 08710"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ISVLSI.2019.00105"},{"key":"ref30","article-title":"A survey of quantization methods for efficient neural network inference","author":"gholami","year":"2021","journal-title":"Low-Power Computer Vision Improve the Efficiency of Artificial Intelligence"},{"key":"ref33","year":"2022","journal-title":"IEEE Xplore"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2019.2918951"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MPRV.2009.82"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1721654.1721672"},{"key":"ref39","first-page":"1","article-title":"Binarized neural networks","author":"courbariaux","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref38","article-title":"Resiliency of deep neural networks under quantization","author":"sung","year":"2015","journal-title":"arXiv 1511 06488"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/MSSC.2017.2745818"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CICC.2018.8357072"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICECS.2018.8617877"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.23919\/DATE.2018.8342120"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2801293"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2761740"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2890150"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.2976475"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3039858"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.07.045"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10122965.pdf?arnumber=10122965","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,18]],"date-time":"2023-09-18T18:14:53Z","timestamp":1695060893000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10122965\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3275431","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}