{"id":"https://openalex.org/W2612510737","doi":"https://doi.org/10.1109/ijcnn.2017.7966106","title":"DropIn: Making reservoir computing neural networks robust to missing inputs by dropout","display_name":"DropIn: Making reservoir computing neural networks robust to missing inputs by dropout","publication_year":2017,"publication_date":"2017-05-01","ids":{"openalex":"https://openalex.org/W2612510737","doi":"https://doi.org/10.1109/ijcnn.2017.7966106","mag":"2612510737"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2017.7966106","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2017.7966106","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1705.02643","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053890378","display_name":"Davide Bacciu","orcid":"https://orcid.org/0000-0001-5213-2468"},"institutions":[{"id":"https://openalex.org/I108290504","display_name":"University of Pisa","ror":"https://ror.org/03ad39j10","country_code":"IT","type":"education","lineage":["https://openalex.org/I108290504"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Davide Bacciu","raw_affiliation_strings":["Dipartimento di Informatica, Universit\u00e0 di Pisa, Pisa, Italy","Dipartimento di Informatica, Universit\u00e0 di Pisa, Largo B. Pontecorvo, 3, Pisa, Italy"],"affiliations":[{"raw_affiliation_string":"Dipartimento di Informatica, Universit\u00e0 di Pisa, Pisa, Italy","institution_ids":["https://openalex.org/I108290504"]},{"raw_affiliation_string":"Dipartimento di Informatica, Universit\u00e0 di Pisa, Largo B. Pontecorvo, 3, Pisa, Italy","institution_ids":["https://openalex.org/I108290504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042642044","display_name":"Francesco Crecchi","orcid":null},"institutions":[{"id":"https://openalex.org/I108290504","display_name":"University of Pisa","ror":"https://ror.org/03ad39j10","country_code":"IT","type":"education","lineage":["https://openalex.org/I108290504"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Francesco Crecchi","raw_affiliation_strings":["Dipartimento di Informatica, Universit\u00e0 di Pisa, Pisa, Italy","Dipartimento di Informatica, Universit\u00e0 di Pisa, Largo B. Pontecorvo, 3, Pisa, Italy"],"affiliations":[{"raw_affiliation_string":"Dipartimento di Informatica, Universit\u00e0 di Pisa, Pisa, Italy","institution_ids":["https://openalex.org/I108290504"]},{"raw_affiliation_string":"Dipartimento di Informatica, Universit\u00e0 di Pisa, Largo B. Pontecorvo, 3, Pisa, Italy","institution_ids":["https://openalex.org/I108290504"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046475893","display_name":"Davide Morelli","orcid":"https://orcid.org/0000-0002-1041-6793"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Davide Morelli","raw_affiliation_strings":["Biobeats Ltd, London, UK"],"affiliations":[{"raw_affiliation_string":"Biobeats Ltd, London, UK","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5053890378"],"corresponding_institution_ids":["https://openalex.org/I108290504"],"apc_list":null,"apc_paid":null,"fwci":0.2077,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.62265285,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"15","issue":null,"first_page":"2080","last_page":"2087"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9896000027656555,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.78897625207901},{"id":"https://openalex.org/keywords/dropout","display_name":"Dropout (neural networks)","score":0.7657215595245361},{"id":"https://openalex.org/keywords/reservoir-computing","display_name":"Reservoir computing","score":0.6700093150138855},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6527785062789917},{"id":"https://openalex.org/keywords/missing-data","display_name":"Missing data","score":0.6350438594818115},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5844419002532959},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.561620831489563},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5422928333282471},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5375663042068481},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4953083097934723},{"id":"https://openalex.org/keywords/train","display_name":"Train","score":0.4370490312576294},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3636687397956848},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.33630383014678955}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.78897625207901},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.7657215595245361},{"id":"https://openalex.org/C135796866","wikidata":"https://www.wikidata.org/wiki/Q7315328","display_name":"Reservoir computing","level":4,"score":0.6700093150138855},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6527785062789917},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.6350438594818115},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5844419002532959},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.561620831489563},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5422928333282471},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5375663042068481},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4953083097934723},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.4370490312576294},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3636687397956848},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.33630383014678955},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/ijcnn.2017.7966106","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2017.7966106","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1705.02643","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1705.02643","pdf_url":"https://arxiv.org/pdf/1705.02643","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2612510737","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1705.02643","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:arpi.unipi.it:11568/891263","is_oa":false,"landing_page_url":"http://hdl.handle.net/11568/891263","pdf_url":null,"source":{"id":"https://openalex.org/S4377196265","display_name":"CINECA IRIS Institutial research information system (University of Pisa)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I108290504","host_organization_name":"University of Pisa","host_organization_lineage":["https://openalex.org/I108290504"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.1705.02643","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1705.02643","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1705.02643","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1705.02643","pdf_url":"https://arxiv.org/pdf/1705.02643","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321873","display_name":"Ministero dell\u2019Istruzione, dell\u2019Universit\u00e0 e della Ricerca","ror":"https://ror.org/0166hxq48"},{"id":"https://openalex.org/F4320324499","display_name":"Universit\u00e0 di Pisa","ror":"https://ror.org/03ad39j10"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2612510737.pdf","grobid_xml":"https://content.openalex.org/works/W2612510737.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W4919037","https://openalex.org/W394351765","https://openalex.org/W1628911597","https://openalex.org/W1978058660","https://openalex.org/W2044372685","https://openalex.org/W2062622742","https://openalex.org/W2082485091","https://openalex.org/W2095705004","https://openalex.org/W2118706537","https://openalex.org/W2122904721","https://openalex.org/W2128152410","https://openalex.org/W2146332392","https://openalex.org/W2171865010","https://openalex.org/W2539369127","https://openalex.org/W6600213771","https://openalex.org/W6674330103","https://openalex.org/W6675244696","https://openalex.org/W6680302858","https://openalex.org/W6682706280","https://openalex.org/W6685489094"],"related_works":["https://openalex.org/W2963790685","https://openalex.org/W3186738100","https://openalex.org/W3177801194","https://openalex.org/W2945969196","https://openalex.org/W3082426109","https://openalex.org/W2525954470","https://openalex.org/W3039107035","https://openalex.org/W3092101150","https://openalex.org/W2288304434","https://openalex.org/W2963030810","https://openalex.org/W2949346385","https://openalex.org/W143570683","https://openalex.org/W3196219156","https://openalex.org/W1164788885","https://openalex.org/W2800011138","https://openalex.org/W2158476197","https://openalex.org/W2974790478","https://openalex.org/W2493224314","https://openalex.org/W2803823081","https://openalex.org/W3085626879"],"abstract_inverted_index":{"The":[0],"paper":[1],"presents":[2],"a":[3,41,48,52,62,135],"novel,":[4],"principled":[5],"approach":[6],"to":[7,20,96,127,132],"train":[8],"recurrent":[9],"neural":[10,49],"networks":[11,105],"from":[12,117],"the":[13,24,33,65,71,74,78,123,144],"Reservoir":[14,81],"Computing":[15,82],"family":[16],"that":[17,91],"are":[18,92,146],"robust":[19],"missing":[21,138],"part":[22],"of":[23,36,55,59,64,73,80,134,143],"input":[25,67,89],"features":[26],"at":[27],"prediction":[28],"time.":[29],"By":[30],"building":[31],"on":[32],"ensembling":[34],"properties":[35],"Dropout":[37],"regularization,":[38],"we":[39],"propose":[40],"methodology,":[42],"named":[43],"DropIn,":[44],"which":[45],"efficiently":[46],"trains":[47],"model":[50,136],"as":[51,100],"committee":[53],"machine":[54],"subnetworks,":[56],"each":[57],"capable":[58],"predicting":[60],"with":[61],"subset":[63],"original":[66],"features.":[68],"We":[69,109],"discuss":[70],"application":[72,119],"DropIn":[75],"methodology":[76,125],"in":[77,101],"context":[79],"models":[83],"and":[84,106],"targeting":[85],"applications":[86],"characterized":[87],"by":[88],"sources":[90],"unreliable":[93],"or":[94],"prone":[95],"be":[97],"disconnected,":[98],"such":[99,118],"pervasive":[102],"wireless":[103],"sensor":[104],"ambient":[107],"intelligence.":[108],"provide":[110],"an":[111],"experimental":[112],"assessment":[113],"using":[114],"real-world":[115],"data":[116],"domains,":[120],"showing":[121],"how":[122],"Dropin":[124],"allows":[126],"maintain":[128],"predictive":[129],"performances":[130],"comparable":[131],"those":[133],"without":[137],"features,":[139],"even":[140],"when":[141],"20%\u201350%":[142],"inputs":[145],"not":[147],"available.":[148]},"counts_by_year":[{"year":2018,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}