{"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/dropin-making-reservoir-computing-neural","title":"DropIn: Making Reservoir Computing Neural Networks Robust to Missing Inputs by Dropout","arxiv_id":"1705.02643","date":"2017-05-07","proceeding":null,"authors":["Davide Bacciu","Francesco Crecchi","Davide Morelli"],"abstract":"The paper presents a novel, principled approach to train recurrent neural\nnetworks from the Reservoir Computing family that are robust to missing part of\nthe input features at prediction time. By building on the ensembling properties\nof Dropout regularization, we propose a methodology, named DropIn, which\nefficiently trains a neural model as a committee machine of subnetworks, each\ncapable of predicting with a subset of the original input features. We discuss\nthe application of the DropIn methodology in the context of Reservoir Computing\nmodels and targeting applications characterized by input sources that are\nunreliable or prone to be disconnected, such as in pervasive wireless sensor\nnetworks and ambient intelligence. We provide an experimental assessment using\nreal-world data from such application domains, showing how the Dropin\nmethodology allows to maintain predictive performances comparable to those of a\nmodel without missing features, even when 20\\%-50\\% of the inputs are not\navailable.","url_abs":"http://arxiv.org/abs/1705.02643v1","url_pdf":"http://arxiv.org/pdf/1705.02643v1.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":"dropin-making-reservoir-computing-neural","repo_url":"https://github.com/FrancescoCrecchi/DropIn-ESN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[],"methods":[{"method_slug":"dropout","method_name":"Dropout"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}