{"id":"https://openalex.org/W2993910441","doi":null,"title":"Indian Buffet Neural Networks for Continual Learning","display_name":"Indian Buffet Neural Networks for Continual Learning","publication_year":2019,"publication_date":"2019-12-04","ids":{"openalex":"https://openalex.org/W2993910441","mag":"2993910441"},"language":"en","primary_location":{"id":"mag:2993910441","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/1912.02290v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/abs/1912.02290v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Samuel Kessler","orcid":"https://orcid.org/0009-0007-4940-8575","observed_orcids":["https://orcid.org/0009-0007-4940-8575"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Samuel Kessler","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0007-4940-8575","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101775198","display_name":"Vu Nguyen","orcid":"https://orcid.org/0000-0002-0294-4561","observed_orcids":["https://orcid.org/0000-0002-0294-4561"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vu Nguyen","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-0294-4561","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090331439","display_name":"Stefan Zohren","orcid":"https://orcid.org/0000-0002-3392-0394","observed_orcids":["https://orcid.org/0000-0002-3392-0394"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stefan Zohren","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-3392-0394","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5058617210","display_name":"Stephen Roberts","orcid":"https://orcid.org/0000-0002-9305-9268","observed_orcids":["https://orcid.org/0000-0002-9305-9268"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stephen Roberts","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-9305-9268","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.27559998631477356,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.27559998631477356,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.20890000462532043,"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/T10320","display_name":"Neural Networks and Applications","score":0.14309999346733093,"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/indian-buffet-process","display_name":"Indian Buffet Process","score":0.9520000219345093},{"id":"https://openalex.org/keywords/bayesian-neural-networks","display_name":"Bayesian neural networks","score":0.8379999995231628},{"id":"https://openalex.org/keywords/continual-learning","display_name":"continual learning","score":0.9860000014305115},{"id":"https://openalex.org/keywords/reparameterization","display_name":"reparameterization","score":0.6470000147819519},{"id":"https://openalex.org/keywords/resource-allocation","display_name":"resource allocation","score":0.7940000295639038},{"id":"https://openalex.org/keywords/overfitting-and-underfitting","display_name":"overfitting and underfitting","score":0.8610000014305115}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8311877250671387},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7195279598236084},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.665598452091217},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6021673679351807},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5216619968414307},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5130183100700378},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.5091230273246765},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.49919557571411133},{"id":"https://openalex.org/C152361515","wikidata":"https://www.wikidata.org/wiki/Q181328","display_name":"Bernoulli's principle","level":2,"score":0.41493868827819824},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.3765297532081604},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2993910441","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/1912.02290v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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}],"best_oa_location":{"id":"mag:2993910441","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/1912.02290v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1589184028","https://openalex.org/W1795258949","https://openalex.org/W1959608418","https://openalex.org/W2153185114","https://openalex.org/W2168947765","https://openalex.org/W2605043629","https://openalex.org/W2737492962","https://openalex.org/W2766424060","https://openalex.org/W2786446225","https://openalex.org/W2803552920","https://openalex.org/W2912351382","https://openalex.org/W2964121744","https://openalex.org/W3091059129"],"related_works":["https://openalex.org/W3008658065","https://openalex.org/W3017963604","https://openalex.org/W4226278852","https://openalex.org/W3157079704","https://openalex.org/W2993852105","https://openalex.org/W3006989712","https://openalex.org/W3082871683","https://openalex.org/W2967652032","https://openalex.org/W2912351382","https://openalex.org/W4406611798"],"abstract_inverted_index":{"We":[0,29,55,121],"place":[1],"an":[2],"Indian":[3],"Buffet":[4],"process":[5],"(IBP)":[6],"prior":[7,37],"over":[8,131],"the":[9,19,22,36,39,60,74,88,95,104,112],"structure":[10,40],"of":[11,21,41,62,87,106,111],"a":[12,52,128],"Bayesian":[13],"Neural":[14],"Network":[15],"(BNN),":[16],"thus":[17],"allowing":[18],"complexity":[20],"BNN":[23],"to":[24,59],"increase":[25],"and":[26,73,90,97,115],"decrease":[27],"automatically.":[28],"further":[30],"extend":[31],"this":[32,57],"model":[33,58,80],"such":[34],"that":[35,124],"on":[38],"each":[42,109],"hidden":[43],"layer":[44,110],"is":[45],"shared":[46],"globally":[47],"across":[48],"all":[49],"layers,":[50],"using":[51],"Hierarchical-IBP":[53],"(H-IBP).":[54],"apply":[56],"problem":[61],"resource":[63],"allocation":[64],"in":[65,108,134],"Continual":[66],"Learning":[67],"(CL)":[68],"where":[69],"new":[70],"tasks":[71],"occur":[72],"network":[75],"requires":[76],"extra":[77],"resources.":[78],"Our":[79],"uses":[81],"online":[82],"variational":[83],"inference":[84],"with":[85],"reparameterisation":[86],"Bernoulli":[89],"Beta":[91],"distributions,":[92],"which":[93],"constitute":[94],"IBP":[96],"H-IBP":[98],"priors.":[99],"As":[100],"we":[101],"automatically":[102],"learn":[103],"number":[105],"weights":[107],"BNN,":[113],"overfitting":[114],"underfitting":[116],"problems":[117],"are":[118],"largely":[119],"overcome.":[120],"show":[122],"empirically":[123],"our":[125],"approach":[126],"offers":[127],"competitive":[129],"edge":[130],"existing":[132],"methods":[133],"CL.":[135]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2019-12-13T00:00:00"}