{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T14:04:41Z","timestamp":1778767481325,"version":"3.51.4"},"reference-count":37,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2017,6,1]],"date-time":"2017-06-01T00:00:00Z","timestamp":1496275200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2017,6,1]]},"DOI":"10.1109\/tpds.2016.2626289","type":"journal-article","created":{"date-parts":[[2016,11,8]],"date-time":"2016-11-08T19:16:47Z","timestamp":1478632607000},"page":"1703-1714","source":"Crossref","is-referenced-by-count":30,"title":["Parallel Deep Neural Network Training for Big Data on Blue Gene\/Q"],"prefix":"10.1109","volume":"28","author":[{"given":"I-Hsin","family":"Chung","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tara N.","family":"Sainath","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bhuvana","family":"Ramabhadran","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Picheny","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"John","family":"Gunnels","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vernon","family":"Austel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Upendra","family":"Chauhari","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Brian","family":"Kingsbury","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638949"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854668"},{"key":"ref31","article-title":"Improvements in using deep belief networks for large vocabular continuous speech recognition","author":"sainath","year":"2010"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2010.5700829"},{"key":"ref37","year":"0"},{"key":"ref36","first-page":"1","article-title":"Predicting parallel application performance via machine\n learning approaches","volume":"19","author":"singh","year":"2006","journal-title":"Concurrency Comput Practice Experience"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2004.8"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707747"},{"key":"ref10","first-page":"735","article-title":"Deep learning via Hessian-free optimization","author":"martens","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960445"},{"key":"ref12","first-page":"2595","article-title":"Parallelized stochastic gradient descent","author":"zinkevich","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref13","first-page":"2010","article-title":"A practical guide to training restricted Boltzmann machines","author":"hinton","year":"2010","journal-title":"Mach Learn Group Univ Toronto Toronto Canada Tech Rep"},{"key":"ref14","article-title":"Improving training time of deep belief networks through hybrid pre-training and larger batch sizes","author":"sainath","year":"0","journal-title":"Proc NIPS Workshop Log-linear Models"},{"key":"ref15","first-page":"1232","article-title":"Large scale distributed deep networks","author":"dean","year":"2012","journal-title":"Advances Neural Inf Process Syst"},{"key":"ref16","first-page":"281","article-title":"Map-reduce for machine learning on multicore","author":"chu","year":"0","journal-title":"Proc 19th Int Conf Advances Neural Inf Process Syst"},{"key":"ref17","article-title":"Implementing level-3 BLAS with BLIS: Early\n experience","author":"zee","year":"2013","journal-title":"Dept Comput Sci Univ Texas Austin Austin TX Tech Rep TR-13–03"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2012.108"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1147\/JRD.2012.2233371"},{"key":"ref28","article-title":"Shared prefetching to reduce execution skew in multi-threaded systems","author":"eichenberger","year":"2013"},{"key":"ref4","article-title":"Application of pretrained deep neural\n networks to large vocabulary speech recognition","author":"jaitly","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref27","article-title":"Opportunities for parallelism in matrix\n multiplication. FLAME Working Note #71","author":"smith","year":"2013","journal-title":"Dept Comput Sci Univ Texas Austin Austin TX Tech Rep TR-13–20"},{"key":"ref3","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"0","journal-title":"Proc 13th Int Conf Artif Intell Statist"},{"key":"ref6","first-page":"437","article-title":"Conversational\n speech transcription using context-dependent deep neural networks","author":"seide","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref29","article-title":"Making good enough\n$\\ldots$\nbetter: Addressing the multiple objectives of high-performance parallel software with a mixed global-local worldview","author":"gunnels","year":"2012"},{"key":"ref5","first-page":"10","article-title":"Scalable minimum bayes risk training of deep neural network acoustic models using distributed\n hessian-free optimization","author":"kingsbury","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163900"},{"key":"ref7","article-title":"Roles of pre-training and\n fine-tuning in context-dependent DBN-HMMs for real-world speech recognition","author":"yu","year":"0","journal-title":"Proc NIPS Workshop on Deep Learning and Unsupervised Feature Learning"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"ref9","first-page":"265","article-title":"On\n optimization methods for deep learning","author":"le","year":"0","journal-title":"Proc 28th Int Conf Mach Learn"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/2304576.2304609"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1137\/10079923X"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2011.108"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1994.6.1.147"},{"key":"ref23","article-title":"Krylov subspace descent for deep learning","author":"vinyals","year":"0","journal-title":"Proc NIPS Workshop Optimiz Hierarch Learn"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960445"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1162\/08997660260028683"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/7927510\/07738586.pdf?arnumber=7738586","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:39:31Z","timestamp":1642005571000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7738586\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,6,1]]},"references-count":37,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2016.2626289","relation":{},"ISSN":["1045-9219"],"issn-type":[{"value":"1045-9219","type":"print"}],"subject":[],"published":{"date-parts":[[2017,6,1]]}}}