{"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/mean-field-networks","title":"Mean-Field Networks","arxiv_id":"1410.5884","date":"2014-10-21","proceeding":null,"authors":["Yujia Li","Richard Zemel"],"abstract":"The mean field algorithm is a widely used approximate inference algorithm for\ngraphical models whose exact inference is intractable. In each iteration of\nmean field, the approximate marginals for each variable are updated by getting\ninformation from the neighbors. This process can be equivalently converted into\na feedforward network, with each layer representing one iteration of mean field\nand with tied weights on all layers. This conversion enables a few natural\nextensions, e.g. untying the weights in the network. In this paper, we study\nthese mean field networks (MFNs), and use them as inference tools as well as\ndiscriminative models. Preliminary experiment results show that MFNs can learn\nto do inference very efficiently and perform significantly better than mean\nfield as discriminative models.","url_abs":"http://arxiv.org/abs/1410.5884v1","url_pdf":"http://arxiv.org/pdf/1410.5884v1.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":"mean-field-networks","repo_url":"https://github.com/romba050/MFN_RBV_segmentation","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}