{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T10:11:19Z","timestamp":1773137479526,"version":"3.50.1"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Korea governmen","award":["RS-2024-00438027"],"award-info":[{"award-number":["RS-2024-00438027"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3667968","type":"journal-article","created":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T20:57:49Z","timestamp":1772053069000},"page":"34404-34419","source":"Crossref","is-referenced-by-count":0,"title":["Swish-T: Enhancing Swish Activation With Tanh-Based Bias for Improved Neural Network Performance"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-9076-5631","authenticated-orcid":false,"given":"Youngmin","family":"Seo","sequence":"first","affiliation":[{"name":"Department of Artificial Intelligence, Sogang University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1052-2170","authenticated-orcid":false,"given":"Jinha","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence, Sogang University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5539-9520","authenticated-orcid":false,"given":"Unsang","family":"Park","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Sogang University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/35016072"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459469"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.5555\/3104322.3104425"},{"key":"ref4","first-page":"3","article-title":"Rectifier nonlinearities improve neural network acoustic models","volume-title":"Proc. ICML Workshop Deep Learn. Audio, Speech Lang. Process.","author":"Maas"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2018.8546022"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-10269-x"},{"key":"ref8","article-title":"Trainable activation function in image classification","author":"Liao","year":"2020","journal-title":"arXiv:2004.13271"},{"key":"ref9","article-title":"Gaussian error linear units (GELUs)","author":"Hendrycks","year":"2016","journal-title":"arXiv:1606.08415"},{"key":"ref10","article-title":"Fast and accurate deep network learning by exponential linear units (ELUs)","author":"Clevert","year":"2015","journal-title":"arXiv:1511.07289"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1710.05941"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00794"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.5244\/C.34.191"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2017.12.012"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00087"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i6.20557"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ISETC50328.2020.9301059"},{"key":"ref18","article-title":"E-swish: Adjusting activations to different network depths","author":"Alcaide","year":"2018","journal-title":"arXiv:1801.07145"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SACI51354.2021.9465622"},{"key":"ref20","article-title":"Maxout networks","author":"Goodfellow","year":"2013","journal-title":"arXiv:1302.4389"},{"key":"ref21","first-page":"6659","article-title":"Bias also matters: Bias attribution for deep neural network explanation","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Wang"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01161"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688253"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3356232"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ISCC50000.2020.9219587"},{"key":"ref27","article-title":"Beyond regression: New tools for prediction and analysis in the behavioral sciences","author":"Werbos","year":"1974"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.4.541"},{"key":"ref29","article-title":"TensorFlow: Large-scale machine learning on heterogeneous systems","author":"Abadi","year":"2015"},{"key":"ref30","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"Paszke","year":"2019","journal-title":"arXiv:1912.01703"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729392"},{"key":"ref33","article-title":"SGDR: Stochastic gradient descent with warm restarts","author":"Loshchilov","year":"2016","journal-title":"arXiv:1608.03983"},{"key":"ref34","article-title":"MNIST handwritten digit database","author":"LeCun","year":"2010","journal-title":"ATT Labs"},{"key":"ref35","article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","author":"Xiao","year":"2017","journal-title":"arXiv:1708.07747"},{"key":"ref36","first-page":"1","article-title":"Reading digits in natural images with unsupervised feature learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Netzer"},{"key":"ref37","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-025-07164-3"},{"key":"ref39","first-page":"1","article-title":"Handwritten digit recognition with a back-propagation network","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"2","author":"LeCun"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref43","first-page":"1","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Tan"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01388"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref46","article-title":"GLU variants improve transformer","author":"Shazeer","year":"2020","journal-title":"arXiv:2002.05202"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref49","article-title":"Tiny ImageNet visual recognition challenge","author":"Le","year":"2015"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.3115\/1620853.1620921"},{"key":"ref53","first-page":"1","article-title":"Incorporating second-order functional knowledge for better option pricing","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"13","author":"Dugas"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"ref55","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref56","first-page":"1","article-title":"Learning robust global representations by penalizing local predictive power","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"32","author":"Wang"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref58","volume-title":"Understanding GPU Memory 1: Visualizing All Allocations Over Time","author":"Shi","year":"2023"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11411783.pdf?arnumber=11411783","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T19:59:21Z","timestamp":1773086361000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11411783\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3667968","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}