{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T07:00:34Z","timestamp":1760598034612,"version":"3.37.3"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3066842","type":"journal-article","created":{"date-parts":[[2021,3,17]],"date-time":"2021-03-17T19:49:20Z","timestamp":1616010560000},"page":"48519-48530","source":"Crossref","is-referenced-by-count":11,"title":["Homogeneous Vector Capsules Enable Adaptive Gradient Descent in Convolutional Neural Networks"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9124-5008","authenticated-orcid":false,"given":"Adam","family":"Byerly","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4859-7152","authenticated-orcid":false,"given":"Tatiana","family":"Kalganova","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","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":"ref32","article-title":"Generalized capsule networks with trainable routing procedure","author":"chen","year":"2018","journal-title":"arXiv 1808 08692"},{"key":"ref31","first-page":"446","article-title":"Food-101–mining discriminative components with random forests","author":"bossard","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"journal-title":"Imagenette","year":"2018","author":"howard","key":"ref30"},{"key":"ref36","first-page":"9098","article-title":"STAR-CAPS: Capsule networks with straight-through attentive routing","author":"ahmed","year":"2019","journal-title":"Proc 33rd Conf Neural Inf Process Syst (NeurIPS)"},{"key":"ref35","article-title":"Network in network","author":"lin","year":"2013","journal-title":"arXiv 1312 4400"},{"key":"ref34","first-page":"1","article-title":"Averaging weights leads to wider optima and better generalization","author":"izmailov","year":"2018","journal-title":"Proc 34th Conf Uncertainty Artif Intell (UAI)"},{"key":"ref10","article-title":"Closing the generalization gap of adaptive gradient methods in training deep neural networks","author":"chen","year":"2018","journal-title":"arXiv 1806 06763"},{"key":"ref11","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"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref15","first-page":"4278","article-title":"Inception-v4, inception-resnet and the impact of residual connections on learning","author":"szegedy","year":"2016","journal-title":"Proc AAAI"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref17","first-page":"1","article-title":"Building deep equivariant capsule networks","author":"venkataraman","year":"0","journal-title":"Proc Int Conf Learn Represent 2020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-020-10273-0"},{"key":"ref19","article-title":"An artificial neural network architecture based on context transformations in cortical minicolumns","author":"morzhakov","year":"2017","journal-title":"arXiv 1712 05954"},{"key":"ref28","first-page":"1","article-title":"Reading digits in natural images with unsupervised feature learning","author":"netzer","year":"2011","journal-title":"Proc NIPS Workshop Deep Learn Unsupervised Feature Learn"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.1315150"},{"key":"ref27","article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","author":"xiao","year":"2017","journal-title":"ArXiv 1708 07747"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref6","first-page":"1","article-title":"Matrix capsules with em routing","author":"hinton","year":"2018","journal-title":"Proc 6th Int Conf Learn Represent (ICLR)"},{"article-title":"Learning multiple layers of features from tiny images","year":"2009","author":"krizhevsky","key":"ref29"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","article-title":"Maximum likelihood from incomplete data via the EM algorithm","volume":"39","author":"dempster","year":"1977","journal-title":"J Roy Statist Soc B Statist Methodol"},{"key":"ref8","first-page":"2121","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"duchi","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref7","first-page":"1","article-title":"The marginal value of adaptive gradient methods in machine learning","author":"wilson","year":"2018","journal-title":"Proc 31st Conf Neural Inf Process Syst"},{"key":"ref2","first-page":"1","article-title":"Dynamic routing between capsules","author":"sabour","year":"2017","journal-title":"Proc 31st Conf Neural Inf Process Syst (NIPS)"},{"key":"ref9","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"Proc 6th Int Conf Learn Represent (ICLR)"},{"key":"ref1","first-page":"44","article-title":"Transforming auto-encoders","author":"hinton","year":"2011","journal-title":"Proc Int Conf Artif Neural Netw"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1113\/jphysiol.1968.sp008455"},{"key":"ref22","article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017","journal-title":"arXiv 1704 04861"},{"key":"ref21","article-title":"Effects of degradations on deep neural network architectures","author":"roy","year":"2018","journal-title":"arXiv 1807 10108"},{"key":"ref24","first-page":"1","article-title":"Self-routing capsule networks","author":"hahn","year":"2019","journal-title":"Proc 33rd Conf Neural Inf Process Syst (NeurIPS)"},{"key":"ref23","article-title":"Pushing the limits of capsule networks","author":"nair","year":"2021","journal-title":"arxiv 2103 08074"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00731"},{"key":"ref25","first-page":"489","article-title":"Capsule networks need an improved routing algorithm","author":"paik","year":"2019","journal-title":"Proc 11th Asian Conf Mach Learn"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09380277.pdf?arnumber=9380277","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,26]],"date-time":"2024-08-26T05:31:05Z","timestamp":1724650265000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9380277\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3066842","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2021]]}}}