{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,11]],"date-time":"2026-01-11T00:27:41Z","timestamp":1768091261380,"version":"3.49.0"},"reference-count":69,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","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":[[2020,10]]},"DOI":"10.1109\/tnnls.2019.2953622","type":"journal-article","created":{"date-parts":[[2020,1,21]],"date-time":"2020-01-21T12:24:16Z","timestamp":1579609456000},"page":"4267-4278","source":"Crossref","is-referenced-by-count":30,"title":["Continual Learning of Recurrent Neural Networks by Locally Aligning Distributed Representations"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2590-1310","authenticated-orcid":false,"given":"Alexander","family":"Ororbia","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5813-3584","authenticated-orcid":false,"given":"Ankur","family":"Mali","sequence":"additional","affiliation":[]},{"given":"C. Lee","family":"Giles","sequence":"additional","affiliation":[]},{"given":"Daniel","family":"Kifer","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2018.2791984"},{"key":"ref38","doi-asserted-by":"crossref","first-page":"3738","DOI":"10.1109\/TNNLS.2017.2735903","article-title":"Exploiting spatio-temporal structure with recurrent winner-take-all networks","volume":"29","author":"santana","year":"2018","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/S0042-6989(97)00169-7"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.19-13-05493.1999"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2004.04.006"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcss.2004.04.001"},{"key":"ref37","article-title":"Deep predictive coding networks for video prediction and unsupervised learning","author":"lotter","year":"2016","journal-title":"arXiv 1605 08104"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2014.2360060"},{"key":"ref35","article-title":"Deep predictive coding networks","author":"chalasani","year":"2013","journal-title":"arXiv 1301 3541"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2013.00276"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.282"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2582924"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2927369"},{"key":"ref28","first-page":"1601","article-title":"The recurrent temporal restricted Boltzmann machine","author":"sutskever","year":"2009","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2018.2884996"},{"key":"ref27","article-title":"Sparse attentive backtracking: Long-range credit assignment in recurrent networks","author":"ke","year":"2017","journal-title":"arXiv 1711 02326"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/S0079-7421(08)60536-8"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/72.501732"},{"key":"ref29","volume":"5","author":"jaeger","year":"2002","journal-title":"Tutorial on Training Recurrent Neural Networks Covering BPPT RTRL EKF and the Echo State Network Approach"},{"key":"ref67","first-page":"2302","article-title":"Never ending learning","author":"mitchell","year":"2015","journal-title":"Proc AAAI"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-012-5320-9"},{"key":"ref69","article-title":"Online semi-supervised learning with deep hybrid Boltzmann machines and denoising autoencoders","author":"ororbia","year":"2015","journal-title":"arXiv 1511 06964"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2006.10.016"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/34.868677"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-23528-8_31"},{"key":"ref22","first-page":"1345","article-title":"Modeling human motion using binary latent variables","author":"taylor","year":"2007","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3389\/fncom.2017.00024"},{"key":"ref24","article-title":"Training recurrent networks online without backtracking","author":"ollivier","year":"2015","journal-title":"arXiv 1507 07680"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.2.270"},{"key":"ref26","article-title":"Approximating real-time recurrent learning with random Kronecker factors","author":"mujika","year":"2018","journal-title":"arXiv 1805 10842"},{"key":"ref25","article-title":"Unbiased online recurrent optimization","author":"tallec","year":"2017","journal-title":"arXiv 1702 05043"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/S1364-6613(98)01241-8"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/1281192.1281225"},{"key":"ref59","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":"ref58","doi-asserted-by":"publisher","DOI":"10.21236\/ADA273556"},{"key":"ref57","article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","author":"xiao","year":"2017","journal-title":"ArXiv 1708 07747"},{"key":"ref56","first-page":"843","article-title":"Unsupervised learning of video representations using LSTMs","volume":"37","author":"srivastava","year":"2015","journal-title":"Proc Int Conf Int Conf Mach Learn (ICML)"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/5.58337"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(88)90007-X"},{"key":"ref53","article-title":"Gradient-based learning algorithms for recurrent networks and their computational complexity","volume":"433","author":"williams","year":"1995","journal-title":"Backpropagation Theory Architectures and Applications"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1080\/09540098908915631"},{"key":"ref10","article-title":"A neural temporal model for human motion prediction","author":"gopalakrishnan","year":"2018","journal-title":"arXiv 1809 03036"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref40","doi-asserted-by":"crossref","first-page":"1150","DOI":"10.1109\/TNNLS.2018.2862866","article-title":"Fast inference predictive coding: A novel model for constructing deep neural networks","volume":"30","author":"song","year":"2019","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref12","article-title":"Learning to adapt by minimizing discrepancy","author":"ororbia","year":"2017","journal-title":"arXiv 1711 11542"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"696","DOI":"10.7551\/mitpress\/4943.003.0042","article-title":"Learning representations by back-propagating errors","author":"rumelhart","year":"1988","journal-title":"Neurocomputing Foundations of Research"},{"key":"ref14","article-title":"Deep credit assignment by aligning local representations","author":"ororbia","year":"2018","journal-title":"arXiv 1803 01834"},{"key":"ref15","article-title":"Biologically motivated algorithms for propagating local target representations","author":"ororbia","year":"2018","journal-title":"arXiv 1805 11703"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1038\/4580"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2012.00620"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.4.721"},{"key":"ref19","article-title":"Random feedback weights support learning in deep neural networks","author":"lillicrap","year":"2014","journal-title":"arXiv 1411 0247"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/0010-0285(72)90002-3"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539871"},{"key":"ref6","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"arXiv 1409 0473"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"612","DOI":"10.1609\/aaai.v24i1.7689","article-title":"Integrating sample-based planning and model-based reinforcement learning","author":"walsh","year":"2010","journal-title":"Proc AAAI"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_01017"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"1045","DOI":"10.21437\/Interspeech.2010-343","article-title":"Recurrent neural network based language model","volume":"2","author":"mikolov","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1996.8.5.895"},{"key":"ref9","first-page":"422","article-title":"Piecewise latent variables for neural variational text processing","author":"serban","year":"2017","journal-title":"Proc Conf Empirical Methods Natural Lang Process"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.79.8.2554"},{"key":"ref45","first-page":"153","article-title":"Greedy layer-wise training of deep networks","volume":"19","author":"bengio","year":"2007","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s10339-007-0167-x"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.4896-03.2004"},{"key":"ref42","article-title":"Decoupled neural interfaces using synthetic gradients","author":"jaderberg","year":"2016","journal-title":"arXiv 1608 05343"},{"key":"ref41","first-page":"485","article-title":"Kickback cuts backprop’s red-tape: Biologically plausible credit assignment in neural networks","author":"balduzzi","year":"2015","journal-title":"Proc AAAI"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-23528-8_32"},{"key":"ref43","first-page":"1037","article-title":"Direct feedback alignment provides learning in deep neural networks","author":"n\u00f8kland","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/9212662\/08963851.pdf?arnumber=8963851","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,30]],"date-time":"2024-07-30T12:33:36Z","timestamp":1722342816000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8963851\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10]]},"references-count":69,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2019.2953622","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,10]]}}}