{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T20:19:24Z","timestamp":1740169164948,"version":"3.37.3"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"National Research Fund (FNR), Luxembourg","award":["R-AGR-0424-05-D\/Bj\u00f6rn"],"award-info":[{"award-number":["R-AGR-0424-05-D\/Bj\u00f6rn"]}]},{"DOI":"10.13039\/501100001866","name":"Ottersten and Project","doi-asserted-by":"publisher","award":["CPPP17\/IS\/11643091\/IDform\/Aouada"],"award-info":[{"award-number":["CPPP17\/IS\/11643091\/IDform\/Aouada"]}],"id":[{"id":"10.13039\/501100001866","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.3026423","type":"journal-article","created":{"date-parts":[[2020,9,24]],"date-time":"2020-09-24T20:30:09Z","timestamp":1600979409000},"page":"176758-176773","source":"Crossref","is-referenced-by-count":3,"title":["Improved Highway Network Block for Training Very Deep Neural Networks"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4652-1691","authenticated-orcid":false,"given":"Oyebade K.","family":"Oyedotun","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8730-3765","authenticated-orcid":false,"given":"Abd El Rahman","family":"Shabayek","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7576-2064","authenticated-orcid":false,"given":"Djamila","family":"Aouada","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2298-6774","authenticated-orcid":false,"given":"Bjorn","family":"Ottersten","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","first-page":"1","article-title":"Revise saturated activation functions","author":"xu","year":"2016","journal-title":"Proc Workshop Int Conf Learn Represent"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2015.7301312"},{"key":"ref32","first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"2015","journal-title":"Proc Int Conf Med Image Comput Comput -Assist Intervent"},{"key":"ref31","article-title":"Visualizing the loss landscape of neural nets","author":"li","year":"2017","journal-title":"arXiv 1712 09913"},{"key":"ref30","article-title":"Demystifying ResNet","author":"li","year":"2016","journal-title":"arXiv 1611 01186"},{"key":"ref37","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref35","first-page":"818","article-title":"Visualizing and understanding convolutional networks","author":"zeiler","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref34","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref10","article-title":"Learning functions: When is deep better than shallow","author":"mhaskar","year":"2016","journal-title":"arXiv 1603 00988"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2293637"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.374"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICSAI.2016.7811085"},{"key":"ref14","first-page":"23","article-title":"Training very deep networks via residual learning with stochastic input shortcut connections","author":"oyedotun","year":"2017","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref15","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":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref17","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref18","first-page":"630","article-title":"Identity mappings in deep residual networks","author":"he","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00217"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"3560","DOI":"10.1109\/TNNLS.2017.2730179","article-title":"Prototype-incorporated emotional neural network","volume":"29","author":"oyedotun","year":"2018","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref28","first-page":"342","article-title":"The shattered gradients problem: If resnets are the answer, then what is the question?","author":"balduzzi","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8296593"},{"key":"ref27","first-page":"971","article-title":"Self-normalizing neural networks","author":"klambauer","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461436"},{"key":"ref5","first-page":"2627","article-title":"Convolutional kernel networks","author":"mairal","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref29","article-title":"Norm-preservation: Why residual networks can become extremely deep?","author":"zaeemzadeh","year":"2018","journal-title":"arXiv 1805 07477"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref7","first-page":"2377","article-title":"Training very deep networks","author":"srivastava","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"ref9","first-page":"666","article-title":"Shallow vs. Deep sum-product networks","volume":"2011","author":"delalleau","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00056"},{"key":"ref46","article-title":"Memory-efficient implementation of DenseNets","author":"pleiss","year":"2017","journal-title":"arXiv 1707 06990"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298958"},{"key":"ref45","article-title":"Evolving deep convolutional neural networks for image classification","author":"sun","year":"2017","journal-title":"arXiv 1710 10741"},{"key":"ref22","first-page":"1","article-title":"Fractalnet: Ultra-deep neural networks without residuals","author":"larsson","year":"2017","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref21","first-page":"562","article-title":"Deeply-supervised nets","author":"lee","year":"2015","journal-title":"Proc Artif Intell Statist"},{"key":"ref42","first-page":"87.1","article-title":"Wide residual networks","author":"zagoruyko","year":"2016","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref24","first-page":"646","article-title":"Deep networks with stochastic depth","author":"huang","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref41","article-title":"Striving for simplicity: The all convolutional net","author":"tobias springenberg","year":"2014","journal-title":"arXiv 1412 6806"},{"key":"ref23","article-title":"Network in network","author":"lin","year":"2013","journal-title":"arXiv 1312 4400"},{"key":"ref44","article-title":"DiracNets: Training very deep neural networks without skip-connections","author":"zagoruyko","year":"2017","journal-title":"arXiv 1706 00388"},{"key":"ref26","article-title":"Exact solutions to the nonlinear dynamics of learning in deep linear neural networks","author":"saxe","year":"2013","journal-title":"arXiv 1312 6120"},{"key":"ref43","first-page":"1319","article-title":"Maxout networks","author":"goodfellow","year":"2013","journal-title":"Proc 30th Int Conf Int Conf Mach Learn"},{"key":"ref25","article-title":"The exploding gradient problem demystified–definition, prevalence, impact, origin, tradeoffs, and solutions","author":"philipp","year":"2017","journal-title":"arXiv 1712 05577"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09205301.pdf?arnumber=9205301","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:56:10Z","timestamp":1639770970000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9205301\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/access.2020.3026423","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2020]]}}}