{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T18:38:15Z","timestamp":1769539095356,"version":"3.49.0"},"reference-count":32,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61806086"],"award-info":[{"award-number":["61806086"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2016M601737"],"award-info":[{"award-number":["2016M601737"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Project of National Key Research and Development Program of China","award":["2018YFB0804204"],"award-info":[{"award-number":["2018YFB0804204"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2019.2939851","type":"journal-article","created":{"date-parts":[[2019,9,9]],"date-time":"2019-09-09T20:24:27Z","timestamp":1568060667000},"page":"62439-62447","source":"Crossref","is-referenced-by-count":2,"title":["The Asynchronous Training Algorithm Based on Sampling and Mean Fusion for Distributed RNN"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6351-3004","authenticated-orcid":false,"given":"Dejiao","family":"Niu","sequence":"first","affiliation":[{"name":"School of Computer Science and Telecommunication Engineering, Jiangsu University, Zhenjiang, China"}]},{"given":"Tianquan","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Telecommunication Engineering, Jiangsu University, Zhenjiang, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1423-2710","authenticated-orcid":false,"given":"Tao","family":"Cai","sequence":"additional","affiliation":[{"name":"School of Computer Science and Telecommunication Engineering, Jiangsu University, Zhenjiang, China"}]},{"given":"Shijie","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Computer Science and Telecommunication Engineering, Jiangsu University, Zhenjiang, China"}]}],"member":"263","reference":[{"key":"ref32","first-page":"29","article-title":"A challenge set for advancing language modeling","author":"zweig","year":"2012","journal-title":"Proc NAACL-HLT Workshop Will Ever Really Replace N-Gram Model Future Language Modeling HLT Assoc Comput Linguistics"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21236\/ADA273556"},{"key":"ref30","first-page":"9","article-title":"Online learning and stochastic approximations","volume":"19","year":"1998","journal-title":"On-Line Learning on Neural Networks"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref12","article-title":"Recent advances in recurrent neural networks","author":"salehinejad","year":"2018","journal-title":"arXiv 1801 01078"},{"key":"ref13","first-page":"1223","article-title":"Large scale distributed deep networks","author":"dean","year":"2012","journal-title":"Proc NIPS"},{"key":"ref14","article-title":"Faster asynchronous SGD","author":"odena","year":"2016","journal-title":"arXiv 1601 04033"},{"key":"ref15","first-page":"2350","article-title":"Staleness-aware Async-SGD for distributed deep learning","author":"zhang","year":"2016","journal-title":"Proc IJCAI"},{"key":"ref16","first-page":"66","article-title":"Predicting statistics of asynchronous SGD parameters for a large-scale distributed deep learning system on GPU supercomputers","author":"oyama","year":"2017","journal-title":"Proc ICB"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2017.21"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1137\/0330046"},{"key":"ref4","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"arXiv 1409 0473"},{"key":"ref27","article-title":"One weird trick for parallelizing convolutional neural networks","author":"krizhevsky","year":"2014","journal-title":"arXiv 1404 5997"},{"key":"ref3","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"arXiv 1409 3215 [cs]"},{"key":"ref6","article-title":"Fast and accurate recurrent neural network acoustic models for speech recognition","author":"sak","year":"2015","journal-title":"arXiv 1507 06947"},{"key":"ref29","article-title":"Towards optimal one pass large scale learning with averaged stochastic gradient descent","author":"xu","year":"2011","journal-title":"arXiv 1107 2490"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref8","article-title":"Are you talking to a machine? Dataset and methods for multilingual image question answering","author":"gao","year":"2015","journal-title":"arXiv 1505 05612"},{"key":"ref7","article-title":"Tensor-train recurrent neural networks for video classification","author":"yang","year":"2017","journal-title":"arXiv 1707 01786"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1107"},{"key":"ref9","article-title":"Training recurrent answering units with joint loss minimization for VQA","author":"noh","year":"2016","journal-title":"arXiv 1606 03647"},{"key":"ref1","first-page":"1045","article-title":"Recurrent neural network based language model","author":"mikolov","year":"2010","journal-title":"Proc ISCA"},{"key":"ref20","first-page":"1","article-title":"To prune, or not to prune: Exploring the efficacy of pruning for model compression","author":"zhu","year":"2018","journal-title":"Proc ICLR"},{"key":"ref22","first-page":"2074","article-title":"Learning structured sparsity in deep neural networks","author":"wen","year":"2016","journal-title":"Proc NIPS"},{"key":"ref21","first-page":"1509","article-title":"TernGrad: Ternary gradients to reduce communication in distributed deep learning","author":"wen","year":"2017","journal-title":"Proc NIPS"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178923"},{"key":"ref23","article-title":"Simple recurrent units for highly parallelizable recurrence","author":"lei","year":"2017","journal-title":"arXiv 1709 02755"},{"key":"ref26","first-page":"1","article-title":"MXNet: A flexible and efficient machine learning library for heterogeneous distributed systems","author":"chen","year":"2015","journal-title":"Proc NIPS"},{"key":"ref25","article-title":"Sliced recurrent neural networks","author":"yu","year":"2018","journal-title":"arXiv 1807 02291"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/08827466.pdf?arnumber=8827466","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T06:00:19Z","timestamp":1769493619000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8827466\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/access.2019.2939851","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}