{"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/processing-of-missing-data-by-neural-networks","title":"Processing of missing data by neural networks","arxiv_id":"1805.07405","date":"2018-05-18","proceeding":"NeurIPS 2018 12","authors":["Marek Smieja","Łukasz Struski","Jacek Tabor","Bartosz Zieliński","Przemysław Spurek"],"abstract":"We propose a general, theoretically justified mechanism for processing\nmissing data by neural networks. Our idea is to replace typical neuron's\nresponse in the first hidden layer by its expected value. This approach can be\napplied for various types of networks at minimal cost in their modification.\nMoreover, in contrast to recent approaches, it does not require complete data\nfor training. Experimental results performed on different types of\narchitectures show that our method gives better results than typical imputation\nstrategies and other methods dedicated for incomplete data.","url_abs":"http://arxiv.org/abs/1805.07405v3","url_pdf":"http://arxiv.org/pdf/1805.07405v3.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":"processing-of-missing-data-by-neural-networks","repo_url":"https://github.com/lstruski/Processing-of-missing-data-by-neural-networks","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"imputation","task_name":"Imputation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.07405","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}