{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T05:23:27Z","timestamp":1725773007965},"reference-count":13,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014,5]]},"DOI":"10.1109\/icassp.2014.6854928","type":"proceedings-article","created":{"date-parts":[[2014,7,29]],"date-time":"2014-07-29T19:23:23Z","timestamp":1406661803000},"page":"6854-6858","source":"Crossref","is-referenced-by-count":6,"title":["Exploring one pass learning for deep neural network training with averaged stochastic gradient descent"],"prefix":"10.1109","author":[{"given":"Zhao","family":"You","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaorui","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638963"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638950"},{"key":"12","first-page":"2121","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","author":"duchi","year":"2011","journal-title":"The Journal of Machine Learning Research"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163900"},{"key":"2","doi-asserted-by":"crossref","first-page":"437","DOI":"10.21437\/Interspeech.2011-169","article-title":"Conversational speech transcription using context-dependent deep neural networks","author":"seide","year":"2011","journal-title":"InterSpeech"},{"key":"1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2109382"},{"key":"10","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"ASRU"},{"key":"7","doi-asserted-by":"crossref","DOI":"10.21236\/ADA164453","author":"rumelhart","year":"1985","journal-title":"Learning Internal Representations by Error Propagation"},{"key":"6","first-page":"177","article-title":"Large-scale machine learning with stochastic gradient descent","author":"le?on","year":"2010","journal-title":"Proceedings of COMPSTAT'2010"},{"journal-title":"Towards Optimal One Pass Large Scale Learning with Averaged Stochastic Gradient Descent","year":"2011","author":"xu","key":"5"},{"key":"4","doi-asserted-by":"publisher","DOI":"10.1137\/0330046"},{"key":"9","article-title":"Krylov subspace descent for deep learning","author":"vinyals","year":"2012","journal-title":"AISTATS"},{"key":"8","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-3","article-title":"Scalable minimum bayes risk training of deep neural network acoustic models using distributed hessian-free optimization","author":"kingsbury","year":"2012","journal-title":"InterSpeech"}],"event":{"name":"ICASSP 2014 - 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2014,5,4]]},"location":"Florence, Italy","end":{"date-parts":[[2014,5,9]]}},"container-title":["2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6844297\/6853544\/06854928.pdf?arnumber=6854928","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,13]],"date-time":"2022-04-13T00:32:21Z","timestamp":1649809941000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6854928\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,5]]},"references-count":13,"URL":"https:\/\/doi.org\/10.1109\/icassp.2014.6854928","relation":{},"subject":[],"published":{"date-parts":[[2014,5]]}}}