{"url":"/method/elish","slug":"elish","name":"ELiSH","full_name":"Exponential Linear Squashing Activation","full_name_withheld":false,"description_markdown":"The **Exponential Linear Squashing Activation Function**, or **ELiSH**, is an activation function used for neural networks. It shares common properties with [Swish](https://paperswithcode.com/method/swish), being made up of an [ELU](https://paperswithcode.com/method/elu) and a [Sigmoid](https://paperswithcode.com/method/sigmoid-activation):\r\n\r\n$$f\\left(x\\right) = \\frac{x}{1+e^{-x}} \\text{ if } x \\geq 0 $$\r\n$$f\\left(x\\right) = \\frac{e^{x} - 1}{1+e^{-x}} \\text{ if } x < 0 $$\r\n\r\nThe Sigmoid part of **ELiSH** improves information flow, while the linear parts solve issues of vanishing gradients.","description_state":"present","introduced_year":null,"introduced_by":{"title":"The Quest for the Golden Activation Function","paper":"/paper/the-quest-for-the-golden-activation-function","first_author":"Mina Basirat","n_authors":2,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/the-quest-for-the-golden-activation-function"},"source":{"url":"http://arxiv.org/abs/1808.00783v1","title":"The Quest for the Golden Activation Function","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/digantamisra98/Echo/blob/ffac8cab7938d8a2ea1eee9a947602d1f577c9f3/echoAI/Activation/Torch/elish.py#L20","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/the-quest-for-the-golden-activation-function","title":"The Quest for the Golden Activation Function","date":"2018-08-02","arxiv_id":"1808.00783","n_code_links":0,"syntology":null}],"papers_shown":1,"tasks":[{"task":"/task/image-classification","name":"Image Classification","papers":1},{"task":"/task/image-classification","name":"image-classification","papers":1}],"tasks_shown":2,"n_tasks":2,"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/elish"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}