{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T18:35:45Z","timestamp":1740162945291,"version":"3.37.3"},"reference-count":31,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Emerg. Sel. Topics Circuits Syst."],"published-print":{"date-parts":[[2019,6]]},"DOI":"10.1109\/jetcas.2019.2918317","type":"journal-article","created":{"date-parts":[[2019,5,22]],"date-time":"2019-05-22T20:00:16Z","timestamp":1558555216000},"page":"247-252","source":"Crossref","is-referenced-by-count":2,"title":["Custom Sub-Systems and Circuits for Deep Learning: Guest Editorial Overview"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5542-7149","authenticated-orcid":false,"given":"Chia-Yu","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3417-8782","authenticated-orcid":false,"given":"Boris","family":"Murmann","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4551-7789","authenticated-orcid":false,"given":"Jae-Sun","family":"Seo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6661-4879","authenticated-orcid":false,"given":"Hoi-Jun","family":"Yoo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2015.7063058"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2017.3711641"},{"key":"ref10","first-page":"1737","article-title":"Deep learning with limited numerical precision","author":"gupta","year":"2015","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.23919\/DATE.2018.8342119"},{"key":"ref12","first-page":"1","article-title":"AdaComp: Adaptive residual gradient compression for data-parallel distributed training","author":"chen","year":"2018","journal-title":"Proc AAAI Conf Artif Intell (AAAI)"},{"key":"ref13","first-page":"1","article-title":"Scalable distributed DNN training using commodity GPU cloud computing","author":"strom","year":"2015","journal-title":"Proc Annu Conf Int Speech Commun Assoc (Interspeech)"},{"key":"ref14","first-page":"1509","article-title":"TernGrad: Ternary gradients to reduce communication in distributed deep learning","author":"wen","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref15","first-page":"1223","article-title":"Large scale distributed deep networks","author":"dean","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2016.0028"},{"key":"ref17","first-page":"5330","article-title":"Can decentralized algorithms outperform centralized algorithms? A case study for decentralized parallel stochastic gradient descent","author":"lian","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/2541940.2541967"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2014.58"},{"key":"ref28","article-title":"A 481pJ\/decision 3.4M decision\/s multifunctional deep in-memory inference processor using standard 6T SRAM Array","author":"kang","year":"2016","journal-title":"arXiv 1610 07501"},{"journal-title":"Inside volta The world's most advanced data center gpu","year":"2017","author":"durant","key":"ref4"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ISVLSI.2017.117"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952564"},{"key":"ref6","article-title":"DoReFa-Net: Training low bitwidth convolutional neural networks with low bitwidth gradients","author":"zhou","year":"2016","journal-title":"arXiv 1606 06160 [cs]"},{"key":"ref29","first-page":"1","article-title":"A machine-learning classifier implemented in a standard 6T SRAM array","author":"zhang","year":"2016","journal-title":"Proc IEEE Symp VLSI Circuits (VLSI)"},{"key":"ref5","article-title":"Quantized neural networks: Training neural networks with low precision weights and activations","author":"hubara","year":"2016","journal-title":"arXiv 1609 07061 [cs]"},{"key":"ref8","article-title":"Pruning convolutional neural networks for resource efficient inference","author":"molchanov","year":"2016","journal-title":"arXiv 1611 06440"},{"key":"ref7","article-title":"DSD: Dense-sparse-dense training for deep neural networks","author":"han","year":"2016","journal-title":"arXiv 1607 04381"},{"key":"ref2","article-title":"Google’s neural machine translation system: Bridging the gap between human and machine translation","author":"wu","year":"2016","journal-title":"arXiv 1609 08144"},{"key":"ref9","article-title":"Net-Trim: Convex pruning of deep neural networks with performance guarantee","author":"aghasi","year":"2016","journal-title":"arXiv 1611 05162"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref20","first-page":"1","article-title":"Invited: Accelerator design for deep learning training","author":"agrawal","year":"2017","journal-title":"Proc ACM\/IEEE Design Automat Conf (DAC)"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021736"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3061639.3062207"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.2017.8050344"},{"key":"ref26","first-page":"222","article-title":"An always-on \n$3.8~\\mu\\text{J}$\n\/86% CIFAR-10 mixed-signal binary CNN processor with all memory on chip in 28 nm CMOS","author":"bankman","year":"2018","journal-title":"IEEE Int Solid-State Circuits Conf (ISSCC) Dig Tech Papers"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2016.2616357"}],"container-title":["IEEE Journal on Emerging and Selected Topics in Circuits and Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5503868\/8734723\/08720273.pdf?arnumber=8720273","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T02:54:35Z","timestamp":1657853675000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8720273\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,6]]},"references-count":31,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/jetcas.2019.2918317","relation":{},"ISSN":["2156-3357","2156-3365"],"issn-type":[{"type":"print","value":"2156-3357"},{"type":"electronic","value":"2156-3365"}],"subject":[],"published":{"date-parts":[[2019,6]]}}}