{"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/a-neural-transfer-function-for-a-smooth-and","title":"A Neural Transfer Function for a Smooth and Differentiable Transition Between Additive and Multiplicative Interactions","arxiv_id":"1503.05724","date":"2015-03-19","proceeding":null,"authors":["Sebastian Urban","Patrick van der Smagt"],"abstract":"Existing approaches to combine both additive and multiplicative neural units\neither use a fixed assignment of operations or require discrete optimization to\ndetermine what function a neuron should perform. This leads either to an\ninefficient distribution of computational resources or an extensive increase in\nthe computational complexity of the training procedure.\n  We present a novel, parameterizable transfer function based on the\nmathematical concept of non-integer functional iteration that allows the\noperation each neuron performs to be smoothly and, most importantly,\ndifferentiablely adjusted between addition and multiplication. This allows the\ndecision between addition and multiplication to be integrated into the standard\nbackpropagation training procedure.","url_abs":"http://arxiv.org/abs/1503.05724v3","url_pdf":"http://arxiv.org/pdf/1503.05724v3.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":"a-neural-transfer-function-for-a-smooth-and","repo_url":"https://github.com/taoketao/force_flows","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}