{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T09:23:24Z","timestamp":1780046604247,"version":"3.53.1"},"reference-count":26,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T00:00:00Z","timestamp":1635724800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T00:00:00Z","timestamp":1635724800000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T00:00:00Z","timestamp":1635724800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T00:00:00Z","timestamp":1635724800000},"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","award":["1741431"],"award-info":[{"award-number":["1741431"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CCF-1718195"],"award-info":[{"award-number":["CCF-1718195"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100011038","name":"Office of the Director of National Intelligence","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100011038","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100011039","name":"Intelligence Advanced Research Projects Activity","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100011039","id-type":"DOI","asserted-by":"publisher"}]},{"name":"IARPA R&D","award":["D17PC00345"],"award-info":[{"award-number":["D17PC00345"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2021,11,1]]},"DOI":"10.1109\/tpami.2020.2990339","type":"journal-article","created":{"date-parts":[[2020,4,28]],"date-time":"2020-04-28T00:18:56Z","timestamp":1588033136000},"page":"3980-3990","source":"Crossref","is-referenced-by-count":54,"title":["Norm-Preservation: Why Residual Networks Can Become Extremely Deep?"],"prefix":"10.1109","volume":"43","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2980-1787","authenticated-orcid":false,"given":"Alireza","family":"Zaeemzadeh","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nazanin","family":"Rahnavard","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8216-1128","authenticated-orcid":false,"given":"Mubarak","family":"Shah","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Identity matters in deep learning","author":"hardt","year":"2017","journal-title":"Proc 5th Int Conf Learn Representations"},{"key":"ref11","first-page":"586","article-title":"Deep learning without poor local minima","author":"kawaguchi","year":"2016","journal-title":"Proc 30th Int Conf Neural Inf Process Syst"},{"key":"ref12","first-page":"342","article-title":"The shattered gradients problem: If resnets are the answer, then what is the question?","volume":"70","author":"balduzzi","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref13","first-page":"550","article-title":"Residual networks behave like ensembles of relatively shallow networks","author":"veit","year":"2016","journal-title":"Proc 29th Int Conf Neural Inf Process Syst"},{"key":"ref14","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":"ref15","article-title":"Density estimation using Real NVP","author":"dinh","year":"2017","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref16","first-page":"2211","article-title":"The reversible residual network: Backpropagation without storing activations","author":"gomez","year":"2017","journal-title":"Proc 31st Int Conf Neural Inf Process Syst"},{"key":"ref17","first-page":"573","article-title":"Invertible residual networks","volume":"97","author":"behrmann","year":"2019","journal-title":"Proc 36th Int Conf Mach Learn"},{"key":"ref18","article-title":"Representing smooth functions as compositions of near-identity functions with implications for deep network optimization","author":"bartlett","year":"2018"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.06.009"},{"key":"ref4","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc 32nd Int Conf Mach Learn"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref7","first-page":"2377","article-title":"Training very deep networks","author":"srivastava","year":"2015","journal-title":"Proc 28th Int Conf Neural Inf Process Syst"},{"key":"ref2","first-page":"2924","article-title":"On the number of linear regions of deep neural networks","author":"montufar","year":"2014","journal-title":"Proc 27th Int Conf Neural Inf Process Syst"},{"key":"ref9","article-title":"Skip connections eliminate singularities","author":"orhan","year":"2018","journal-title":"Proc 6th Int Conf Learn Representations"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref20","first-page":"9482","article-title":"Implicit bias of gradient descent on linear convolutional networks","author":"gunasekar","year":"2018","journal-title":"Proc 32nd Int Conf Neural Inf Process Syst"},{"key":"ref22","article-title":"The singular values of convolutional layers","author":"sedghi","year":"2019","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref21","first-page":"1729","article-title":"Train longer, generalize better: Closing the generalization gap in large batch training of neural networks","author":"hoffer","year":"2017","journal-title":"Proc 31st Int Conf Neural Inf Process Syst"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1023\/A:1019150005407"},{"key":"ref23","volume":"30","author":"gower","year":"2004","journal-title":"et al"},{"key":"ref26","article-title":"EraseReLU: A simple way to ease the training of deep convolution neural networks","author":"dong","year":"2017"},{"key":"ref25","article-title":"Learning multiple layers of features from tiny images.(2009)","author":"krizhevsky","year":"2009","journal-title":"Technical Report TR-2009"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/34\/9556112\/9079218-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/9556112\/09079218.pdf?arnumber=9079218","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:49:26Z","timestamp":1652194166000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9079218\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,1]]},"references-count":26,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2020.2990339","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,11,1]]}}}