{"url":"/method/colu","slug":"colu","name":"CoLU","full_name":"Collapsing Linear Unit","full_name_withheld":false,"description_markdown":"CoLU is an activation function similar to Swish and Mish in properties. It is defined as:\r\n$$f(x)=\\frac{x}{1-x^{-(x+e^x)}}$$\r\nIt is smooth, continuously differentiable, unbounded above, bounded below, non-saturating, and non-monotonic. Based on experiments done with CoLU with different activation functions, it is observed that CoLU usually performs better than other functions on deeper neural networks.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Deeper Learning with CoLU Activation","paper":"/paper/deeper-learning-with-colu-activation","first_author":"Advait Vagerwal","n_authors":1,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/deeper-learning-with-colu-activation"},"source":{"url":"https://arxiv.org/abs/2112.12078v1","title":"Deeper Learning with CoLU Activation","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"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/deeper-learning-with-colu-activation","title":"Deeper Learning with CoLU Activation","date":"2021-12-18","arxiv_id":"2112.12078","n_code_links":0,"syntology":null}],"papers_shown":1,"tasks":[],"tasks_shown":0,"n_tasks":0,"usage_by_year":[{"year":"2021","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/colu"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}