{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T02:48:04Z","timestamp":1784774884204,"version":"3.55.0"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61773117"],"award-info":[{"award-number":["61773117"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61403081"],"award-info":[{"award-number":["61403081"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61502095"],"award-info":[{"award-number":["61502095"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61602260"],"award-info":[{"award-number":["61602260"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61170165"],"award-info":[{"award-number":["61170165"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61702279"],"award-info":[{"award-number":["61702279"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National High Technology Research and Development Program (863 Program) of China","award":["2015AA015406"],"award-info":[{"award-number":["2015AA015406"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2020,3]]},"DOI":"10.1109\/tnnls.2019.2910302","type":"journal-article","created":{"date-parts":[[2019,5,4]],"date-time":"2019-05-04T02:01:06Z","timestamp":1556935266000},"page":"813-826","source":"Crossref","is-referenced-by-count":35,"title":["Recurrent Neural Networks With External Addressable Long-Term and Working Memory for Learning Long-Term Dependences"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1748-8586","authenticated-orcid":false,"given":"Zhibin","family":"Quan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weili","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuelian","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5219-2812","authenticated-orcid":false,"given":"Yandong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunxiu","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6385-6776","authenticated-orcid":false,"given":"Wankou","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"26","article-title":"Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude","volume":"4","author":"tieleman","year":"2012","journal-title":"COURSERA Neural Netw Mach Learn"},{"key":"ref38","first-page":"2121","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"duchi","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref33","author":"santoro","year":"2016","journal-title":"One-shot learning with memory-augmented neural networks"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3758\/BF03204624"},{"key":"ref31","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proc 32nd Int Conf Mach Learn"},{"key":"ref30","author":"andrychowicz","year":"2016","journal-title":"Learning Efficient Algorithms with Hierarchical Attentive Memory[J]"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/5.58337"},{"key":"ref36","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref35","author":"hinton","year":"2012","journal-title":"Improving Neural Networks by Preventing Co-adaptation of Feature Detectors"},{"key":"ref34","author":"gulcehre","year":"2016","journal-title":"Dynamic neural Turing machine with soft and hard addressing schemes"},{"key":"ref28","author":"zaremba","year":"2015","journal-title":"Reinforcement learning neural turing machines"},{"key":"ref27","article-title":"Towards AI-complete question answering: A set of prerequisite toy tasks","author":"weston","year":"2016","journal-title":"Proc 4th Int Conf Learn Represent (ICLR)"},{"key":"ref29","first-page":"115","article-title":"Learning precise timing with LSTM recurrent networks","volume":"3","author":"gers","year":"2002","journal-title":"J Mach Learn Res"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/72.279181"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(96)00105-0"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/S0028-3932(02)00169-0"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1016\/S0079-6123(07)00020-9","article-title":"What are the differences between long-term, short-term, and working memory","volume":"169","author":"cowan","year":"2008","journal-title":"Progr Brain Res"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1038\/nrn1201"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2582924"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2015.04.006"},{"key":"ref26","first-page":"2440","article-title":"End-to-end memory networks","author":"sukhbaatar","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref25","author":"weston","year":"2014","journal-title":"Memory networks"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2485259"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2016.7510235"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2017.7510820"},{"key":"ref10","author":"graves","year":"2014","journal-title":"Neural Turing machines"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/nature20101"},{"key":"ref40","author":"kingma","year":"2014","journal-title":"Adam A method for stochastic optimization"},{"key":"ref12","author":"ma","year":"2017","journal-title":"Long-Term Memory Networks for Question Answering [J]"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2884540"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00729"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2851077"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1146"},{"key":"ref17","first-page":"1","article-title":"Memory architectures in recurrent neural network language models","author":"yogatama","year":"2018","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref18","first-page":"1","article-title":"Memory augmented control networks","author":"khan","year":"2018","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2677968"},{"key":"ref4","first-page":"735","article-title":"Deep learning via hessian-free optimization","author":"martens","year":"2010","journal-title":"Proc 27th Int Conf Mach Learn (ICML)"},{"key":"ref3","first-page":"1310","article-title":"On the difficulty of training recurrent neural networks","author":"pascanu","year":"2013","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref6","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref5","first-page":"1033","article-title":"Learning recurrent neural networks with hessian-free optimization","author":"martens","year":"2011","journal-title":"Proc 28th Int Conf Mach Learn"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref7","first-page":"2067","article-title":"Gated feedback recurrent neural networks","author":"chung","year":"2015","journal-title":"Proc 32nd Int Conf Mach Learn (ICML)"},{"key":"ref49","author":"mikolov","year":"2014","journal-title":"Learning longer memory in recurrent neural networks"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21236\/ADA273556"},{"key":"ref45","first-page":"1","article-title":"Three approaches to the quantitative definition of information","volume":"1","author":"kolmogorov","year":"1965","journal-title":"Problems Inf Transmiss"},{"key":"ref48","author":"zaremba","year":"2014","journal-title":"Recurrent Neural Network Regularization"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947611"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref41","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"2010","journal-title":"Proc 13th Int Conf Artif Intell Statist"},{"key":"ref44","author":"team","year":"2016","journal-title":"Theano A Python framework for fast computation of mathematical expressions"},{"key":"ref43","author":"chollet","year":"2015","journal-title":"Keras"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/9018332\/08705689.pdf?arnumber=8705689","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:19:31Z","timestamp":1651079971000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8705689\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3]]},"references-count":52,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2019.2910302","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,3]]}}}