{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T12:35:01Z","timestamp":1743078901582,"version":"3.37.3"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/OAPA.html"}],"funder":[{"name":"National Key R&D Program of China","award":["2017YFB0202201"],"award-info":[{"award-number":["2017YFB0202201"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U161126"],"award-info":[{"award-number":["U161126"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"crossref","award":["61872392"],"award-info":[{"award-number":["61872392"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Program for Guangdong Introducing Innovative and Entrepreneurial Teams","award":["2016ZT06D211"],"award-info":[{"award-number":["2016ZT06D211"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2018]]},"DOI":"10.1109\/access.2018.2879877","type":"journal-article","created":{"date-parts":[[2018,11,9]],"date-time":"2018-11-09T22:00:21Z","timestamp":1541800821000},"page":"69660-69671","source":"Crossref","is-referenced-by-count":3,"title":["SingleCaffe: An Efficient Framework for Deep Learning on a Single Node"],"prefix":"10.1109","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1276-5759","authenticated-orcid":false,"given":"Chenxu","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yixian","family":"Shen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jia","family":"Jia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yutong","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiguang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"571","article-title":"Project adam: Building an efficient and scalable deep learning training system","volume":"14","author":"chilimbi","year":"2014","journal-title":"Proc OSDI"},{"journal-title":"Caffe Website","year":"2018","key":"ref38"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2015.2472014"},{"journal-title":"Mxnet A flexible and efficient machine learning library for heterogeneous distributed systems","year":"2015","author":"chen","key":"ref32"},{"key":"ref31","article-title":"GeePS: Scalable deep learning on distributed GPUs with a GPU-specialized parameter server","author":"cui","year":"2016","journal-title":"Proc 11th Eur Conf Comput Syst"},{"key":"ref30","first-page":"1223","article-title":"More effective distributed ML via a stale synchronous parallel parameter server","author":"ho","year":"2013","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref37","first-page":"1","article-title":"Scaling learning algorithms towards AI","volume":"34","author":"bengio","year":"2007","journal-title":"Large Scale Kernel Machines"},{"journal-title":"MXNET-MPI Embedding MPI parallelism in parameter server task model for scaling deep learning","year":"2018","author":"mamidala","key":"ref36"},{"key":"ref35","first-page":"800","article-title":"Theano-MPI: A theano-based distributed training framework","author":"ma","year":"2016","journal-title":"Proc Eur Conf Parallel Process"},{"journal-title":"Distributed tensorflow with mpi","year":"2016","author":"vishnu","key":"ref34"},{"key":"ref10","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/0167-8191(96)00024-5"},{"journal-title":"Caffenet","year":"2018","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"journal-title":"Network in Network","year":"2013","author":"lin","key":"ref13"},{"journal-title":"Very Deep Convolutional Networks for Large-scale Image Recognition","year":"2014","author":"simonyan","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"journal-title":"Mxnet A flexible and efficient machine learning library for heterogeneous distributed systems","year":"2015","author":"chen","key":"ref16"},{"journal-title":"Theano new features and speed improvements","year":"2012","author":"bastien","key":"ref17"},{"journal-title":"Tensorflow Large-scale machine learning on heterogeneous distributed systems","year":"2016","author":"abadi","key":"ref18"},{"journal-title":"CNTK","year":"2018","key":"ref19"},{"journal-title":"Deep image Scaling up image recognition","year":"2015","author":"wu","key":"ref28"},{"key":"ref4","first-page":"215","article-title":"An analysis of single-layer networks in unsupervised feature learning","author":"coates","year":"2011","journal-title":"Proc 14th Int Conf Artif Intell Statist"},{"key":"ref27","first-page":"631","article-title":"Litz: Elastic framework for high-performance distributed machine learning","author":"qiao","year":"2018","journal-title":"Proc of USENIX Annual Technical Conf (USENIX)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00052"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390177"},{"key":"ref29","first-page":"583","article-title":"Scaling distributed machine learning with the parameter server","volume":"14","author":"li","year":"2014","journal-title":"Proc OSDI"},{"key":"ref5","first-page":"1137","article-title":"A neural probabilistic language model","volume":"3","author":"bengio","year":"2003","journal-title":"J Mach Learn Res"},{"journal-title":"NVIDIA DRIVE Scalable AI Platform for Autonomous Driving","year":"2018","key":"ref8"},{"journal-title":"Deep learning for identifying metastatic breast cancer","year":"2016","author":"wang","key":"ref7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref9","first-page":"265","article-title":"On optimization methods for deep learning","author":"le","year":"2011","journal-title":"Proc Int Conf Int Conf Mach Learn"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3018743.3018769"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref22","first-page":"1223","article-title":"Large scale distributed deep networks","author":"dean","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.284"},{"key":"ref42","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in Neural Information Processing Systems 25"},{"journal-title":"Large batch training of convolutional networks","year":"2017","author":"you","key":"ref24"},{"key":"ref41","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1007\/3-540-61626-8_16","article-title":"Mpi-2: Extending the message-passing interface","author":"geist","year":"1996","journal-title":"Euro-Par Parallel Processing"},{"journal-title":"Deepbench","year":"2018","key":"ref23"},{"key":"ref44","article-title":"Learning multiple layers of features from tiny images","volume":"1","author":"krizhevsky","year":"2009"},{"key":"ref26","first-page":"1","article-title":"Imagenet training in minutes","author":"you","year":"2018","journal-title":"Proc 47th Int Conf Parallel Process"},{"key":"ref43","first-page":"396","article-title":"Handwritten digit recognition with a back-propagation network","author":"lecun","year":"1990","journal-title":"Advances in Neural Information Processing Systems 2"},{"journal-title":"Accurate large minibatch sgd Training imagenet in 1 hour","year":"2017","author":"goyal","key":"ref25"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8274985\/08528440.pdf?arnumber=8528440","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T02:52:51Z","timestamp":1643251971000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8528440\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/access.2018.2879877","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2018]]}}}