{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T02:03:33Z","timestamp":1771466613472,"version":"3.50.1"},"reference-count":28,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100005049","name":"Science and Engineering Research Council, Agency of Science, Technology and Research, Singapore, through the National Robotics Program","doi-asserted-by":"publisher","award":["1922500054"],"award-info":[{"award-number":["1922500054"]}],"id":[{"id":"10.13039\/501100005049","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":[[2022,10]]},"DOI":"10.1109\/tnnls.2021.3069883","type":"journal-article","created":{"date-parts":[[2021,4,9]],"date-time":"2021-04-09T19:32:26Z","timestamp":1617996746000},"page":"6013-6020","source":"Crossref","is-referenced-by-count":10,"title":["Fully Decoupled Neural Network Learning Using Delayed Gradients"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4612-5445","authenticated-orcid":false,"given":"Huiping","family":"Zhuang","sequence":"first","affiliation":[{"name":"School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8659-4724","authenticated-orcid":false,"given":"Yi","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3869-9171","authenticated-orcid":false,"given":"Qinglai","family":"Liu","sequence":"additional","affiliation":[{"name":"Temasek Laboratories, Nanyang Technological University, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1587-1226","authenticated-orcid":false,"given":"Zhiping","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.87"},{"key":"ref5","article-title":"Beyond regression: New tools for prediction and analysis in the behavioral sciences","author":"Werbos","year":"1974"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9217"},{"key":"ref7","first-page":"1627","article-title":"Decoupled neural interfaces using synthetic gradients","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jaderberg"},{"key":"ref8","first-page":"103","article-title":"Gpipe: Efficient training of giant neural networks using pipeline parallelism","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Huang"},{"key":"ref9","article-title":"Horovod: Fast and easy distributed deep learning in TensorFlow","author":"Sergeev","year":"2018","journal-title":"arXiv:1802.05799"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2953131"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s13398-014-0173-7.2"},{"key":"ref12","first-page":"2103","article-title":"Decoupled parallel backpropagation with convergence guarantee","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Huo"},{"key":"ref13","first-page":"6659","article-title":"Training neural networks using features replay","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Huo"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms13276"},{"key":"ref15","first-page":"1037","article-title":"Direct feedback alignment provides learning in deep neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"N\u00f8kland"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2756859"},{"key":"ref17","first-page":"9368","article-title":"Assessing the scalability of biologically-motivated deep learning algorithms and architectures","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bartunov"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2018.00608"},{"key":"ref19","first-page":"4839","article-title":"Training neural networks with local error signals","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"N\u00f8kland"},{"key":"ref20","first-page":"736","article-title":"Decoupled greedy learning of CNNs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Belilovsky"},{"key":"ref21","first-page":"4120","article-title":"Asynchronous stochastic gradient descent with delay compensation","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","volume":"70","author":"Zheng"},{"key":"ref22","first-page":"950","article-title":"A simple weight decay can improve generalization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"4","author":"Krogh"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1137\/16M1080173"},{"key":"ref24","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref27","article-title":"Adding gradient noise improves learning for very deep networks","author":"Neelakantan","year":"2015","journal-title":"arXiv:1511.06807"},{"key":"ref28","volume-title":"CNN-Benchmarks","year":"2017"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/9911935\/09399673.pdf?arnumber=9399673","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T23:00:40Z","timestamp":1704841240000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9399673\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10]]},"references-count":28,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2021.3069883","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10]]}}}