{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T07:31:31Z","timestamp":1771659091923,"version":"3.50.1"},"reference-count":64,"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.2021.3105355","type":"journal-article","created":{"date-parts":[[2021,8,16]],"date-time":"2021-08-16T20:21:44Z","timestamp":1629145304000},"page":"120613-120623","source":"Crossref","is-referenced-by-count":18,"title":["TanhSoft\u2014Dynamic Trainable Activation Functions for Faster Learning and Better Performance"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9818-8966","authenticated-orcid":false,"given":"Koushik","family":"Biswas","sequence":"first","affiliation":[{"name":"Department of Computer Science, IIIT Delhi, New Delhi, India"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5464-929X","authenticated-orcid":false,"given":"Sandeep","family":"Kumar","sequence":"additional","affiliation":[{"name":"Department of Computer Science, IIIT Delhi, New Delhi, India"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1036-9576","authenticated-orcid":false,"given":"Shilpak","family":"Banerjee","sequence":"additional","affiliation":[{"name":"Department of Mathematics, IIIT Delhi, New Delhi, India"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9723-035X","authenticated-orcid":false,"given":"Ashish Kumar","family":"Pandey","sequence":"additional","affiliation":[{"name":"Department of Mathematics, IIIT Delhi, New Delhi, India"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015"},{"key":"ref38","article-title":"Tiny imagenet visual recognition challenge","author":"le","year":"2015"},{"key":"ref33","article-title":"Universal approximation with deep narrow networks","author":"kidger","year":"2020"},{"key":"ref32","article-title":"Padé activation units: End-to-end learning of flexible activation functions in deep networks","author":"molina","year":"2020"},{"key":"ref31","article-title":"Tanhexp: A smooth activation function with high convergence speed for lightweight neural networks","author":"liu","year":"2020"},{"key":"ref30","article-title":"Designing neural network architectures using reinforcement learning","author":"baker","year":"2016"},{"key":"ref37","article-title":"Reading digits in natural images with unsupervised feature learning","author":"netzer","year":"2011"},{"key":"ref36","article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","author":"xiao","year":"2017","journal-title":"ArXiv 1708 07747"},{"key":"ref35","first-page":"451","article-title":"Incorporating second-order functional knowledge for better option pricing","author":"dugas","year":"2000","journal-title":"Proc 13th Int Conf Neural Inf Process Syst (NIPS)"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.4.541"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729392"},{"key":"ref62","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-24574-4_28","article-title":"U-Net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"2015"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref63","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume":"9","author":"glorot","year":"2010","journal-title":"Proc 13th Int Conf Artif Intell Statist"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/S0165-1889(02)00157-4"},{"key":"ref64","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(96)00006-8"},{"key":"ref29","article-title":"Deeparchitect: Automatically designing and training deep architectures","author":"negrinho","year":"2017"},{"key":"ref2","first-page":"807","article-title":"Rectified linear units improve restricted Boltzmann machines","author":"nair","year":"2010","journal-title":"Proc 27th Int Conf Mach Learn (ICML)"},{"key":"ref1","article-title":"Activation functions: Comparison of trends in practice and research for deep learning","author":"nwankpa","year":"2018","journal-title":"arXiv 1811 03378"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref24","article-title":"Sigmoid-weighted linear units for neural network function approximation in reinforcement learning","author":"elfwing","year":"2017"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2017.00038"},{"key":"ref26","article-title":"Mish: A self regularized non-monotonic activation function","author":"misra","year":"2019"},{"key":"ref25","article-title":"Gaussian error linear units (GELUs)","author":"hendrycks","year":"2020"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00907"},{"key":"ref51","article-title":"Resnet in Resnet: Generalizing residual architectures","author":"targ","year":"2016","journal-title":"arXiv 1603 08029"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"key":"ref58","first-page":"21","article-title":"SSD: Single shot multibox detector","author":"liu","year":"2016","journal-title":"Vision Computer"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref56","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc 3rd Int Conf Learn Represent (ICLR)"},{"key":"ref55","article-title":"SqueezeNet: AlexNet-level accuracy with 50× fewer parameters and ¡0.5mb model size","author":"iandola","year":"2016","journal-title":"arXiv 1602 07360"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref53","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","author":"tan","year":"2020"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2018.8546022"},{"key":"ref11","article-title":"Searching for activation functions","author":"ramachandran","year":"2017"},{"key":"ref40","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":"ref12","article-title":"Language models are unsupervised multitask learners","author":"radford","year":"2019"},{"key":"ref13","article-title":"Yolov4: Optimal speed and accuracy of object detection","author":"bochkovskiy","year":"2020"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3017436"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2015.7280459"},{"key":"ref16","author":"lecun","year":"2010","journal-title":"MNIST Handwritten Digit Database"},{"key":"ref17","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref19","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015"},{"key":"ref4","article-title":"Soft-root-sign activation function","author":"zhou","year":"2020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/35016072"},{"key":"ref6","article-title":"Fast and accurate deep network learning by exponential linear units (ELUs)","author":"clevert","year":"2015","journal-title":"arXiv 1511 07289"},{"key":"ref5","first-page":"3","article-title":"Rectifier nonlinearities improve neural network acoustic models","author":"andrew maas","year":"2013","journal-title":"Proc ICML Workshop Deep Learn Audio Speech Lang Process"},{"key":"ref8","article-title":"Empirical evaluation of rectified activations in convolutional network","author":"xu","year":"2015"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"ref9","article-title":"Improving deep learning by inverse square root linear units (ISRLUs)","author":"carlile","year":"2017","journal-title":"arXiv 1710 09967"},{"key":"ref46","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-46493-0_39","article-title":"Deep networks with stochastic depth","author":"huang","year":"2016"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00255"},{"key":"ref47","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-01264-9_8","article-title":"Shufflenet v2: Practical guidelines for efficient CNN architecture design","author":"ma","year":"2018"},{"key":"ref42","article-title":"Lets keep it simple, using simple architectures to outperform deeper and more complex architectures","author":"hasanpour","year":"2016","journal-title":"arXiv 1608 06037"},{"key":"ref41","first-page":"630","article-title":"Identity mappings in deep residual networks","author":"he","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref43","first-page":"1","article-title":"Wide residual networks","author":"zagoruyko","year":"2016","journal-title":"Proc Brit Mach Vis Conf"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09514829.pdf?arnumber=9514829","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,8]],"date-time":"2022-09-08T20:42:58Z","timestamp":1662669778000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9514829\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3105355","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}