{"url":"/method/aglu","slug":"aglu","name":"AGLU","full_name":"Adaptive Generalised Linear Unit","full_name_withheld":false,"description_markdown":"The Adaptive Parametric activation (APA) is defined as: $APA(z,λ,κ) = (λ exp(−κz) + 1) ^{\\frac{1}{−λ}}$, where $λ$ and $κ$ are learnable parameters. \r\nThis activation function is a generalisation of the Sigmoid and the Gumbel activation functions  and it is expressive and versatile. For example, APA can be used inside the channel attention mechanism instead of the Sigmoid activation,\r\nor it  can be used inside the intermediate layers using the Adaptive Generalised Linear Unit (AGLU): $AGLU(z,λ,κ) = z APA(z,λ,κ)$.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Adaptive Parametric Activation","paper":"/paper/adaptive-parametric-activation","first_author":"Konstantinos Panagiotis Alexandridis","n_authors":4,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/adaptive-parametric-activation"},"source":{"url":"https://arxiv.org/abs/2407.08567v2","title":"Adaptive Parametric 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":"Adaptive Activation Functions","url":"/methods/category/adaptive-activation-functions","pwc_aliases":[]}],"n_papers_tagged":1,"archive_num_papers":1,"papers_newest_first":[{"paper":"/paper/adaptive-parametric-activation","title":"Adaptive Parametric Activation","date":"2024-07-11","arxiv_id":"2407.08567","n_code_links":1,"syntology":null}],"papers_shown":1,"tasks":[{"task":"/task/instance-segmentation","name":"Instance Segmentation","papers":1},{"task":"/task/long-tail-learning","name":"Long-tail Learning","papers":1},{"task":"/task/imbalanced-classification","name":"imbalanced classification","papers":1}],"tasks_shown":3,"n_tasks":3,"usage_by_year":[{"year":"2024","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/aglu"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}