{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T12:23:57Z","timestamp":1777724637095,"version":"3.51.4"},"reference-count":83,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T00:00:00Z","timestamp":1667260800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T00:00:00Z","timestamp":1667260800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T00:00:00Z","timestamp":1667260800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000185","name":"Defense Advanced Research Projects Agency","doi-asserted-by":"publisher","award":["FA9453-18-1-0039"],"award-info":[{"award-number":["FA9453-18-1-0039"]}],"id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","award":["N00014-18-1-2306"],"award-info":[{"award-number":["N00014-18-1-2306"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Comput. Intell. Mag."],"published-print":{"date-parts":[[2022,11,1]]},"DOI":"10.1109\/mci.2022.3199624","type":"journal-article","created":{"date-parts":[[2022,11,8]],"date-time":"2022-11-08T20:31:10Z","timestamp":1667939470000},"page":"39-51","source":"Crossref","is-referenced-by-count":9,"title":["Training Deep Architectures Without End-to-End Backpropagation: A Survey on the Provably Optimal Methods"],"prefix":"10.1109","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4197-3621","authenticated-orcid":false,"given":"Shiyu","family":"Duan","sequence":"first","affiliation":[{"name":"University of Florida, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jose C.","family":"Principe","sequence":"additional","affiliation":[{"name":"University of Florida, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref73","article-title":"Similarity learning for provably accurate sparse linear classification","author":"bellet","year":"2012","journal-title":"Proc 29th Int Conf Mach Learn"},{"key":"ref72","first-page":"287","article-title":"Improved guarantees for learning via similarity functions","author":"balcan","year":"2008","journal-title":"Proc 21st Annu Conf Learn Theory"},{"key":"ref71","first-page":"7313","article-title":"Global convergence of block coordinate descent in deep learning","author":"zeng","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781107298019"},{"key":"ref76","first-page":"215","article-title":"An analysis of single-layer networks in unsupervised feature learning","author":"coates","year":"0","journal-title":"Proc 14th Int Conf Artif Intell Statist"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref74","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009"},{"key":"ref39","article-title":"Principled training of neural networks with direct feedback alignment","author":"launay","year":"2019"},{"key":"ref75","article-title":"Reading digits in natural images with unsupervised feature learning","author":"netzer","year":"2011"},{"key":"ref38","first-page":"5511","article-title":"Two routes to scalable credit assignment without weight symmetry","author":"kunin","year":"2020","journal-title":"Int Conf Mach Learn"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref33","article-title":"Biologically-plausible learning algorithms can scale to large datasets","author":"xiao","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2805098"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2018.00608"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_01374"},{"key":"ref37","article-title":"Spike-based causal inference for weight alignment","author":"guerguiev","year":"2019","journal-title":"Int Conf Learn Representations"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2953622"},{"key":"ref35","article-title":"Kickback cuts backprop’s red-tape: Biologically plausible credit assignment in neural networks","volume":"29","author":"balduzzi","year":"2015","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref34","first-page":"10","article-title":"Distributed optimization of deeply nested systems","author":"carreira-perpinan","year":"0","journal-title":"Proc Artif Intell Statist"},{"key":"ref60","first-page":"7313","article-title":"Global convergence of block coordinate descent in deep learning","author":"zeng","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3017434"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207043"},{"key":"ref63","first-page":"9368","article-title":"Assessing the scalability of biologically-motivated deep learning algorithms and architectures","volume":"31","author":"bartunov","year":"2018","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00929"},{"key":"ref64","first-page":"1193","article-title":"Beyond backprop: Online alternating minimization with auxiliary variables","author":"choromanska","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref27","article-title":"Feedback alignment in deep convolutional networks","author":"moskovitz","year":"2018"},{"key":"ref65","first-page":"22566","article-title":"Can the brain do backpropagation?–exact implementation of backpropagation in predictive coding networks","volume":"33","author":"lukasiewicz","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2018.03.003"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1820458116"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10279"},{"key":"ref68","article-title":"Deriving differential target propagation from iterating approximate inverses","author":"bengio","year":"2020"},{"key":"ref69","first-page":"3039","article-title":"Putting an end to end-to-end: Gradient-isolated learning of representations","author":"l\u00f6we","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/BF02551274"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"key":"ref20","first-page":"583","article-title":"Greedy layerwise learning can scale to imagenet","author":"belilovsky","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref22","first-page":"20024","article-title":"A theoretical framework for target propagation","volume":"33","author":"meulemans","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref21","first-page":"7296","article-title":"Kernelized information bottleneck leads to biologically plausible 3-factor Hebbian learning in deep networks","volume":"33","author":"pogodin","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref24","first-page":"1","article-title":"Target propagation in recurrent neural networks","volume":"21","author":"manchev","year":"2020","journal-title":"J Mach Learn Res"},{"key":"ref23","first-page":"736","article-title":"Decoupled greedy learning of CNNs","author":"belilovsky","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms13276"},{"key":"ref25","first-page":"1037","article-title":"Direct feedback alignment provides learning in deep neural networks","volume":"29","author":"n\u00f8kland","year":"2016","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00949"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_01018"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.165"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014181"},{"key":"ref57","first-page":"276","article-title":"ParMAC: Distributed optimisation of nested functions, with application to learning binary autoencoders","volume":"1","author":"carreira-perpin\u00e1n","year":"2019","journal-title":"Proc Mach Learn Syst"},{"key":"ref56","article-title":"A proximal block coordinate descent algorithm for deep neural network training","author":"lau","year":"2018","journal-title":"Proc 6th Int Conf Learn Representations Workshop Track Proceedings"},{"key":"ref55","article-title":"Lifted neural networks","author":"askari","year":"2018"},{"key":"ref54","first-page":"1721","article-title":"Convergent block coordinate descent for training tikhonov regularized deep neural networks","author":"zhang","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref53","first-page":"3362","article-title":"Fenchel lifted networks: A lagrange relaxation of neural network training","author":"gu","year":"0","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref52","article-title":"A provably correct algorithm for deep learning that actually works","author":"malach","year":"2018"},{"key":"ref10","article-title":"Revisiting locally supervised learning: An alternative to end-to-end training","author":"wang","year":"2020","journal-title":"Int Conf Learn Representations"},{"key":"ref11","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref40","first-page":"2722","article-title":"Training neural networks without gradients: A scalable admm approach","author":"taylor","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref12","first-page":"562","article-title":"Deeply-supervised nets","author":"lee","year":"2015","journal-title":"Proc Artif Intell Statist"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_01250"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-23528-8_31"},{"key":"ref15","first-page":"4839","article-title":"Training neural networks with local error signals","author":"n\u00f8kland","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_01373"},{"key":"ref16","first-page":"1627","article-title":"Decoupled neural interfaces using synthetic gradients","author":"jaderberg","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref81","article-title":"Labels, information, and computation: Efficient, privacy-preserving learning using sufficient labels","author":"duan","year":"2021"},{"key":"ref17","first-page":"904","article-title":"Understanding synthetic gradients and decoupled neural interfaces","author":"czarnecki","year":"2017","journal-title":"Int Conf Mach Learn"},{"key":"ref18","article-title":"Learning to solve the credit assignment problem","author":"lansdell","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref83","first-page":"5628","article-title":"A theoretical analysis of contrastive unsupervised representation learning","author":"saunshi","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref19","article-title":"How auto-encoders could provide credit assignment in deep networks via target propagation","author":"bengio","year":"2014"},{"key":"ref80","article-title":"Explaining and harnessing adversarial examples","author":"goodfellow","year":"2015","journal-title":"Proc 3rd Int Conf Learn Representations"},{"key":"ref4","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"0","journal-title":"Proc Conf North Amer Chapter Assoc Comput Linguistics Hum Lang Technol Volume 1 (Long and Short Papers)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3042346"},{"key":"ref7","article-title":"Why gradient clipping accelerates training: A theoretical justification for adaptivity","author":"zhang","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref49","first-page":"22566","article-title":"Can the brain do backpropagation?–exact implementation of backpropagation in predictive coding networks","volume":"33","author":"song","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref9","first-page":"1","article-title":"Interlocking backpropagation: Improving depthwise model-parallelism","volume":"23","author":"gomez","year":"2022","journal-title":"J Mach Learn Res"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5950"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i11.17202"},{"key":"ref48","first-page":"15403","article-title":"Structured and deep similarity matching via structured and deep Hebbian networks","author":"obeid","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref47","first-page":"2058","article-title":"Learning deep resnet blocks sequentially using boosting theory","author":"huang","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014651"},{"key":"ref41","first-page":"10065","article-title":"Biological credit assignment through dynamic inversion of feedforward networks","volume":"33","author":"podlaski","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3389\/fncom.2017.00024"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2021.633674"}],"container-title":["IEEE Computational Intelligence Magazine"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10207\/9942674\/09942693.pdf?arnumber=9942693","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,5]],"date-time":"2022-12-05T22:20:37Z","timestamp":1670278837000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9942693\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,1]]},"references-count":83,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/mci.2022.3199624","relation":{},"ISSN":["1556-603X","1556-6048"],"issn-type":[{"value":"1556-603X","type":"print"},{"value":"1556-6048","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11,1]]}}}