{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T15:06:40Z","timestamp":1789571200072,"version":"build-2803163510"},"reference-count":30,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.3001531","type":"journal-article","created":{"date-parts":[[2020,6,10]],"date-time":"2020-06-10T20:26:39Z","timestamp":1591820799000},"page":"111626-111635","source":"Crossref","is-referenced-by-count":108,"title":["Approximating the Gradient of Cross-Entropy Loss Function"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7165-5184","authenticated-orcid":false,"given":"Li","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Milos","family":"Doroslovacki","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Murray H.","family":"Loew","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref30","article-title":"Understanding deep learning requires rethinking generalization","author":"zhang","year":"2016","journal-title":"arXiv 1611 03530"},{"key":"ref10","first-page":"7","article-title":"Large-margin softmax loss for convolutional neural networks","volume":"2","author":"liu","year":"2016","journal-title":"Proc ICML"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_31"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1023\/A:1026543900054"},{"key":"ref13","article-title":"Squared earth mover’s distance-based loss for training deep neural networks","author":"hou","year":"2016","journal-title":"arXiv 1611 05916"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.1991.155439"},{"key":"ref15","first-page":"34","article-title":"Loss functions for discriminative training of energy-based models","volume":"6","author":"lecun","year":"2005","journal-title":"Proc AISTATS"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/89.568732"},{"key":"ref17","first-page":"1109","article-title":"Large scale online learning of image similarity through ranking","volume":"11","author":"chechik","year":"2010","journal-title":"J Mach Learn Res"},{"key":"ref18","first-page":"513","article-title":"Neighbourhood components analysis","author":"goldberger","year":"2005","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref19","first-page":"412","article-title":"Learning a nonlinear embedding by preserving class neighbourhood structure","author":"salakhutdinov","year":"2007","journal-title":"Artificial Intelligence and Statistics"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2018.02.010"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IEEECONF44664.2019.9048718"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref3","first-page":"815","article-title":"A tutorial on energy-based learning","volume":"1","author":"lecun","year":"2006","journal-title":"Predicting Structured Data"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00552"},{"key":"ref29","volume":"1","author":"oliphant","year":"2006","journal-title":"A Guide to NumPy"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CISS.2019.8692803"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-76153-9_28"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.713"},{"key":"ref1","author":"karpathy","year":"2019","journal-title":"Convolutional Neural Network for Visual Recognition"},{"key":"ref20","article-title":"Deep linear discriminant analysis","author":"dorfer","year":"2015","journal-title":"arXiv 1511 04707"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref21","first-page":"237","article-title":"Gradient flow in recurrent nets: The difficulty of learning longterm dependencies","author":"kolen","year":"2001","journal-title":"A Field Guide to Dynamical Recurrent Networks"},{"key":"ref24","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.87"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.4467\/20838476SI.16.004.6185"},{"key":"ref25","article-title":"Deep learning using linear support vector machines","author":"tang","year":"2013","journal-title":"arXiv 1306 0239"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09113308.pdf?arnumber=9113308","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:52:38Z","timestamp":1639770758000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9113308\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/access.2020.3001531","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}