{"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/dropout-as-a-bayesian-approximation-appendix","title":"Dropout as a Bayesian Approximation: Appendix","arxiv_id":"1506.02157","date":"2015-06-06","proceeding":null,"authors":["Yarin Gal","Zoubin Ghahramani"],"abstract":"We show that a neural network with arbitrary depth and non-linearities, with\ndropout applied before every weight layer, is mathematically equivalent to an\napproximation to a well known Bayesian model. This interpretation might offer\nan explanation to some of dropout's key properties, such as its robustness to\nover-fitting. Our interpretation allows us to reason about uncertainty in deep\nlearning, and allows the introduction of the Bayesian machinery into existing\ndeep learning frameworks in a principled way.\n  This document is an appendix for the main paper \"Dropout as a Bayesian\nApproximation: Representing Model Uncertainty in Deep Learning\" by Gal and\nGhahramani, 2015.","url_abs":"http://arxiv.org/abs/1506.02157v5","url_pdf":"http://arxiv.org/pdf/1506.02157v5.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":"dropout-as-a-bayesian-approximation-appendix","repo_url":"https://github.com/yaringal/HeteroscedasticDropoutUncertainty","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1506.02157","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}