{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/swish-t-enhancing-swish-activation-with-tanh","title":"Swish-T : Enhancing Swish Activation with Tanh Bias for Improved Neural Network Performance","arxiv_id":"2407.01012","date":"2024-07-01","proceeding":null,"authors":["Youngmin Seo","Jinha Kim","Unsang Park"],"abstract":"We propose the Swish-T family, an enhancement of the existing non-monotonic activation function Swish. Swish-T is defined by adding a Tanh bias to the original Swish function. This modification creates a family of Swish-T variants, each designed to excel in different tasks, showcasing specific advantages depending on the application context. The Tanh bias allows for broader acceptance of negative values during initial training stages, offering a smoother non-monotonic curve than the original Swish. We ultimately propose the Swish-T$_{\\textbf{C}}$ function, while Swish-T and Swish-T$_{\\textbf{B}}$, byproducts of Swish-T$_{\\textbf{C}}$, also demonstrate satisfactory performance. Furthermore, our ablation study shows that using Swish-T$_{\\textbf{C}}$ as a non-parametric function can still achieve high performance. The superiority of the Swish-T family has been empirically demonstrated across various models and benchmark datasets, including MNIST, Fashion MNIST, SVHN, CIFAR-10, and CIFAR-100. The code is publicly available at https://github.com/ictseoyoungmin/Swish-T-pytorch.","url_abs":"https://arxiv.org/abs/2407.01012v3","url_pdf":"https://arxiv.org/pdf/2407.01012v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"swish-t-enhancing-swish-activation-with-tanh","repo_url":"https://github.com/ictseoyoungmin/swish-t-pytorch","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"swish-t-enhancing-swish-activation-with-tanh","repo_url":"https://github.com/MindCode-4/code-9/tree/main/swish-t","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"swish-t-enhancing-swish-activation-with-tanh","repo_url":"https://github.com/pwc-1/Paper-9/tree/main/3/swish-t","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"swish-t-enhancing-swish-activation-with-tanh","repo_url":"https://github.com/pwc-1/Paper-9/tree/main/4/swish-t","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"swish-t-enhancing-swish-activation-with-tanh","repo_url":"https://github.com/reeered/Swish-T-MindSpore","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[],"methods":[{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2407.01012","atlas_url":"https://app.syntology.ai/?focus=2407.01012","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}