{"url":"/method/serlu","slug":"serlu","name":"SERLU","full_name":"SERLU","full_name_withheld":false,"description_markdown":"**SERLU**, or **Scaled Exponentially-Regularized Linear Unit**, is a type of activation function. The new function introduces a bump-shaped function in the region of negative input. The bump-shaped function has approximately zero response to large negative input while being able to push the output of SERLU towards zero mean statistically.\r\n\r\n$$ \\text{SERLU}\\left(x\\right)) = \\lambda\\_{serlu}x \\text{ if } x \\geq 0 $$\r\n$$ \\text{SERLU}\\left(x\\right)) = \\lambda\\_{serlu}\\alpha\\_{serlu}xe^{x} \\text{ if } x < 0 $$\r\n\r\nwhere the two parameters $\\lambda\\_{serlu} > 0$ and $\\alpha\\_{serlu} > 0$ remain to be specified.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Effectiveness of Scaled Exponentially-Regularized Linear Units (SERLUs)","paper":"/paper/effectiveness-of-scaled-exponentially","first_author":"G. Zhang","n_authors":2,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/effectiveness-of-scaled-exponentially"},"source":{"url":"http://arxiv.org/abs/1807.10117v2","title":"Effectiveness of Scaled Exponentially-Regularized Linear Units (SERLUs)","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/mattresnick/Custom-PyTorch-Resources/blob/2e3b05d7e0f75cea22902e9d62ed9869ce4c1c70/ActivationFunctions.py#L10","code_snippet_url_on_a_code_host":true,"categories":[{"area":"General","area_id":"general","collection":"Activation Functions","url":"/methods/category/activation-functions","pwc_aliases":[]}],"n_papers_tagged":1,"archive_num_papers":1,"papers_newest_first":[{"paper":"/paper/effectiveness-of-scaled-exponentially","title":"Effectiveness of Scaled Exponentially-Regularized Linear Units (SERLUs)","date":"2018-07-26","arxiv_id":"1807.10117","n_code_links":0,"syntology":null}],"papers_shown":1,"tasks":[],"tasks_shown":0,"n_tasks":0,"usage_by_year":[{"year":"2018","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/serlu"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}