{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,24]],"date-time":"2026-10-24T12:06:43Z","timestamp":1792843603231,"version":"4.5.0"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"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":["62071484"],"award-info":[{"award-number":["62071484"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2023,4]]},"DOI":"10.1109\/tnnls.2021.3105818","type":"journal-article","created":{"date-parts":[[2021,8,30]],"date-time":"2021-08-30T20:53:40Z","timestamp":1630356820000},"page":"2057-2067","source":"Crossref","is-referenced-by-count":26,"title":["DRRNets: Dynamic Recurrent Routing via Low-Rank Regularization in Recurrent Neural Networks"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6386-6096","authenticated-orcid":false,"given":"Dongjing","family":"Shan","sequence":"first","affiliation":[{"name":"Laboratory of Intelligent Information Processing, Army Engineering University, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2296-6370","authenticated-orcid":false,"given":"Yong","family":"Luo","sequence":"additional","affiliation":[{"name":"National Engineering Research Center for Multimedia Software, School of Computer Science, Institute of Artificial Intelligence, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4890-0668","authenticated-orcid":false,"given":"Xiongwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Speech Processing Laboratory, Army Engineering University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1018-4144","authenticated-orcid":false,"given":"Chao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Machine Perception (MOE), Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2947563"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/100"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2957276"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2979670"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2582924"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/d14-1179"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/nature20101"},{"key":"ref11","first-page":"3882","article-title":"Phased LSTM: Accelerating recurrent network training for long or event-based sequences","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 29, Annu. Conf. Neural Inf. Process. Syst.","author":"Neil"},{"key":"ref12","article-title":"Hierarchical multiscale recurrent neural networks","volume-title":"Proc. 5th Int. Conf. Learn. Represent. (ICLR)","author":"Chung"},{"key":"ref13","first-page":"77","article-title":"Dilated recurrent neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chang"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p17-1172"},{"key":"ref15","article-title":"Skip RNN: Learning to skip state updates in recurrent neural networks","author":"Campos","year":"2017","journal-title":"arXiv:1708.06834"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2009.2022980"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.1315150"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.5555\/2999134.2999257"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-80"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-3410"},{"key":"ref21","article-title":"The concrete distribution: A continuous relaxation of discrete random variables","volume-title":"Proc. 5th Int. Conf. Learn. Represent. (ICLR)","author":"Maddison"},{"key":"ref22","volume-title":"The Unreasonable Effectiveness of the Forget Gate","author":"van der Westhuizen","year":"2018"},{"key":"ref23","volume-title":"Low Rank Structure of Learned Representations","author":"Sanyal","year":"2018"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref25","first-page":"1120","article-title":"Unitary evolution recurrent neural networks","volume-title":"Proc. 33rd Int. Conf. Mach. Learn. (ICML)","author":"Arjovsky"},{"key":"ref26","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. 3rd Int. Conf. Learn. Represent. (ICLR)","author":"Kingma"},{"key":"ref27","first-page":"9017","article-title":"FastGRNN: A fast, accurate, stable and tiny kilobyte sized gated recurrent neural network","volume-title":"Advances in Neural Information Processing Systems","volume":"31","author":"Kusupati","year":"2018"},{"key":"ref28","article-title":"AntisymmetricRNN: A dynamical system view on recurrent neural networks","volume-title":"Proc. 7th Int. Conf. Learn. Represent. (ICLR)","author":"Chang"},{"key":"ref29","article-title":"RNNs incrementally evolving on an equilibrium manifold: A panacea for vanishing and exploding gradients?","volume-title":"Proc. 8th Int. Conf. Learn. Represent. (ICLR)","author":"Kag"},{"key":"ref30","first-page":"2401","article-title":"Efficient orthogonal parametrisation of recurrent neural networks using householder reflections","volume-title":"Proc. 34th Int. Conf. Mach. Learn. (ICML)","volume":"70","author":"Mhammedi"},{"key":"ref31","article-title":"Zoneout: Regularizing RNNs by randomly preserving hidden activations","author":"Krueger","year":"2016","journal-title":"arXiv:1606.01305"},{"key":"ref32","first-page":"4880","article-title":"Full-capacity unitary recurrent neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wisdom"},{"key":"ref33","first-page":"1","article-title":"Wider and deeper, cheaper and faster: Tensorized LSTMs for sequence learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"He"},{"key":"ref34","article-title":"Regularizing and optimizing LSTM language models","author":"Merity","year":"2017","journal-title":"arXiv:1708.02182"},{"key":"ref35","first-page":"1","article-title":"Recurrent batch normalization","volume-title":"Proc. 5th Int. Conf. Learn. Represent. (ICLR)","author":"Cooijmans"},{"key":"ref36","article-title":"Recurrent dropout without memory loss","author":"Semeniuta","year":"2016","journal-title":"arXiv:1603.05118"},{"key":"ref37","article-title":"HyperNetworks","author":"Ha","year":"2016","journal-title":"arXiv:1609.09106"},{"key":"ref38","volume-title":"Recurrent Neural Network Regularization","author":"Zaremba","year":"2014"},{"key":"ref39","volume-title":"An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling","author":"Bai","year":"2018"},{"key":"ref40","first-page":"1019","article-title":"A theoretically grounded application of dropout in recurrent neural networks","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Gal"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10362"},{"key":"ref42","first-page":"1","article-title":"Pointer Sentinel mixture models","volume-title":"Proc. 5th Int. Conf. Learn. Represent. (ICLR)","author":"Merity"},{"key":"ref43","first-page":"1","article-title":"Tying word vectors and word classifiers: A loss framework for language modeling","volume-title":"Proc. 5th Int. Conf. Learn. Represent. (ICLR)","author":"Inan"},{"key":"ref44","first-page":"4189","article-title":"Recurrent highway networks","volume-title":"Proc. 34th Int. Conf. Mach. Learn. (ICML)","volume":"70","author":"Zilly"},{"key":"ref45","first-page":"1","article-title":"Neural architecture search with reinforcement learning","volume-title":"Proc. 5th Int. Conf. Learn. Represent. (ICLR)","author":"Zoph"},{"key":"ref46","first-page":"1","article-title":"On the state of the art of evaluation in neural language models","volume-title":"Proc. 6th Int. Conf. Learn. Represent. (ICLR)","author":"Melis"},{"key":"ref47","article-title":"Mogrifier LSTM","author":"Melis","year":"2019","journal-title":"arXiv:1909.01792"},{"key":"ref48","article-title":"Breaking the softmax bottleneck: A high-rank RNN language model","volume-title":"Proc. 6th Int. Conf. Learn. Represent. (ICLR)","author":"Yang"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2205241"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2011.09.003"},{"key":"ref51","article-title":"Deep speaker: An end-to-end neural speaker embedding system","author":"Li","year":"2017","journal-title":"arXiv:1705.02304"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854363"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10091960\/09525048.pdf?arnumber=9525048","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,11]],"date-time":"2024-01-11T23:06:48Z","timestamp":1705014408000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9525048\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4]]},"references-count":52,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2021.3105818","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4]]}}}