{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T03:05:07Z","timestamp":1791774307794,"version":"4.3.4"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2021,2,1]],"date-time":"2021-02-01T00:00:00Z","timestamp":1612137600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,2,1]],"date-time":"2021-02-01T00:00:00Z","timestamp":1612137600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,2,1]],"date-time":"2021-02-01T00:00:00Z","timestamp":1612137600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2021,2]]},"DOI":"10.1109\/tnnls.2020.2979706","type":"journal-article","created":{"date-parts":[[2020,4,7]],"date-time":"2020-04-07T21:55:02Z","timestamp":1586296502000},"page":"916-924","source":"Crossref","is-referenced-by-count":16,"title":["Enhancing Function Approximation Abilities of Neural Networks by Training Derivatives"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6540-8515","authenticated-orcid":false,"given":"V. I.","family":"Avrutskiy","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"1","article-title":"Neural networks catching up with finite differences in solving partial differential equations in higher dimensions","author":"avrutskiy","year":"2020","journal-title":"Neural Comput Appl"},{"key":"ref38","first-page":"144","article-title":"Preventing overfitting by training derivatives","author":"avrutskiy","year":"2019","journal-title":"Proc Future Technol Conf"},{"key":"ref33","article-title":"Efficient implementation of a higher-order language with built-in AD","author":"siskind","year":"2016","journal-title":"arXiv 1611 03416"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898717761"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.06.056"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/72.165599"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1080\/00207179508921605"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1993.298623"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref34","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":"ref10","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":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472088"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/5326.897072"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.camwa.2011.09.028"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/0895-7177(94)90095-7"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.amc.2006.05.068"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/72.712178"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/S0010-4655(97)00054-4"},{"key":"ref17","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref18","first-page":"1058","article-title":"Regularization of neural networks using dropconnect","author":"wan","year":"2013","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref19","article-title":"Batch-normalized maxout network in network","author":"chang","year":"2015","journal-title":"arXiv 1511 02583"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(91)90009-T"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2011.2128344"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(92)90012-8"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(05)80020-6"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/BF00993164"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/18.256500"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.1999.831531"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2244083"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/BF02551274"},{"key":"ref9","doi-asserted-by":"crossref","DOI":"10.1093\/oso\/9780198538493.001.0001","author":"bishop","year":"1995","journal-title":"Neural Networks for Pattern Recognition"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(89)90020-8"},{"key":"ref46","volume":"15","author":"nvidia","year":"2008","journal-title":"CUBLAS Library"},{"key":"ref20","article-title":"Maxout networks","author":"goodfellow","year":"2013","journal-title":"arXiv 1302 4389"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.37236\/1027"},{"key":"ref48","article-title":"TensorFlow: Large-scale machine learning on heterogeneous distributed systems","author":"abadi","year":"2016","journal-title":"arXiv 1603 04467"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/11559887_7"},{"key":"ref47","article-title":"Theano: Deep learning on GPUs with Python","volume":"3","author":"bergstra","year":"2011","journal-title":"Proc BigLearn Workshop NIPS"},{"key":"ref21","article-title":"All you need is a good init","author":"mishkin","year":"2015","journal-title":"arXiv 1511 06422"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1561\/2200000006"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/72.165600"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/BF00332918"},{"key":"ref23","first-page":"549","article-title":"Transformation invariance in pattern recognition—Tangent distance and tangent propagation","author":"simard","year":"1998","journal-title":"Neural Networks Tricks of the Trade"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1201\/9780203758540"},{"key":"ref26","first-page":"435","article-title":"Differentiating functions of the Jacobian with respect to the weights","author":"flake","year":"2000","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref43","article-title":"Backpropagation generalized for output derivatives","author":"avrutskiy","year":"2017","journal-title":"arXiv 1712 04185"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(00)00013-7"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/9346113\/09058995.pdf?arnumber=9058995","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,3]],"date-time":"2024-08-03T16:31:53Z","timestamp":1722702713000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9058995\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2]]},"references-count":48,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2020.2979706","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,2]]}}}