{"id":"https://openalex.org/W2608358109","doi":"https://doi.org/10.1109/ijcnn.2017.7966158","title":"Recursive autoconvolution for unsupervised learning of convolutional neural networks","display_name":"Recursive autoconvolution for unsupervised learning of convolutional neural networks","publication_year":2017,"publication_date":"2017-05-01","ids":{"openalex":"https://openalex.org/W2608358109","doi":"https://doi.org/10.1109/ijcnn.2017.7966158","mag":"2608358109"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2017.7966158","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2017.7966158","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/1606.00611","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054351253","display_name":"B. A. Knyazev","orcid":"https://orcid.org/0000-0003-4187-3249"},"institutions":[{"id":"https://openalex.org/I177537411","display_name":"Bauman Moscow State Technical University","ror":"https://ror.org/00pb8h375","country_code":"RU","type":"education","lineage":["https://openalex.org/I177537411"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"Boris Knyazev","raw_affiliation_strings":["Bauman Moscow State Technical University","Bauman Moscow State Technical University,"],"affiliations":[{"raw_affiliation_string":"Bauman Moscow State Technical University","institution_ids":["https://openalex.org/I177537411"]},{"raw_affiliation_string":"Bauman Moscow State Technical University,","institution_ids":["https://openalex.org/I177537411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021756032","display_name":"Erhardt Barth","orcid":"https://orcid.org/0000-0001-8556-2472"},"institutions":[{"id":"https://openalex.org/I9341345","display_name":"University of L\u00fcbeck","ror":"https://ror.org/00t3r8h32","country_code":"DE","type":"education","lineage":["https://openalex.org/I9341345"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Erhardt Barth","raw_affiliation_strings":["Institut f\u00fcr Neuro-und Bioinformatik, University of L\u00fcbeck","Institut f\u00fcr Neuro- und Bioinformatik, University of L\u00fcbeck"],"affiliations":[{"raw_affiliation_string":"Institut f\u00fcr Neuro-und Bioinformatik, University of L\u00fcbeck","institution_ids":["https://openalex.org/I9341345"]},{"raw_affiliation_string":"Institut f\u00fcr Neuro- und Bioinformatik, University of L\u00fcbeck","institution_ids":["https://openalex.org/I9341345"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014856404","display_name":"Thomas Martinetz","orcid":"https://orcid.org/0000-0002-4539-4475"},"institutions":[{"id":"https://openalex.org/I9341345","display_name":"University of L\u00fcbeck","ror":"https://ror.org/00t3r8h32","country_code":"DE","type":"education","lineage":["https://openalex.org/I9341345"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thomas Martinetz","raw_affiliation_strings":["Institut f\u00fcr Neuro-und Bioinformatik, University of L\u00fcbeck","Institut f\u00fcr Neuro- und Bioinformatik, University of L\u00fcbeck"],"affiliations":[{"raw_affiliation_string":"Institut f\u00fcr Neuro-und Bioinformatik, University of L\u00fcbeck","institution_ids":["https://openalex.org/I9341345"]},{"raw_affiliation_string":"Institut f\u00fcr Neuro- und Bioinformatik, University of L\u00fcbeck","institution_ids":["https://openalex.org/I9341345"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5054351253"],"corresponding_institution_ids":["https://openalex.org/I177537411"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05546703,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2486","last_page":"2493"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9922000169754028,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9898999929428101,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/mnist-database","display_name":"MNIST database","score":0.9179399013519287},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7224788069725037},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7114269733428955},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7061989307403564},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6902225017547607},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.6833699345588684},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5416157841682434},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5365756750106812},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4943668842315674},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4550441801548004},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4485546052455902},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4227589964866638},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.4224608838558197}],"concepts":[{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.9179399013519287},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7224788069725037},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7114269733428955},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7061989307403564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6902225017547607},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.6833699345588684},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5416157841682434},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5365756750106812},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4943668842315674},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4550441801548004},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4485546052455902},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4227589964866638},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.4224608838558197},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/ijcnn.2017.7966158","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2017.7966158","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:1606.00611","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1606.00611","pdf_url":"https://arxiv.org/pdf/1606.00611","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:2608358109","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1606.00611","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":"doi:10.48550/arxiv.1606.00611","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1606.00611","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:1606.00611","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1606.00611","pdf_url":"https://arxiv.org/pdf/1606.00611","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":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7799999713897705}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320875","display_name":"Deutscher Akademischer Austauschdienst","ror":"https://ror.org/039djdh30"},{"id":"https://openalex.org/F4320321912","display_name":"Ministry of Education and Science of the Russian Federation","ror":"https://ror.org/00ghqgy32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2608358109.pdf","grobid_xml":"https://content.openalex.org/works/W2608358109.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W219040644","https://openalex.org/W1649885719","https://openalex.org/W1963882359","https://openalex.org/W1979931042","https://openalex.org/W1991922259","https://openalex.org/W2066941820","https://openalex.org/W2112796928","https://openalex.org/W2113092041","https://openalex.org/W2117259536","https://openalex.org/W2117756735","https://openalex.org/W2118858186","https://openalex.org/W2141224535","https://openalex.org/W2143214697","https://openalex.org/W2149270675","https://openalex.org/W2151911322","https://openalex.org/W2333630628","https://openalex.org/W2919115771","https://openalex.org/W6623329352","https://openalex.org/W6631708475","https://openalex.org/W6639204139","https://openalex.org/W6676103248","https://openalex.org/W6676759488","https://openalex.org/W6678131844","https://openalex.org/W6678543393","https://openalex.org/W6686418764"],"related_works":["https://openalex.org/W2963468520","https://openalex.org/W2413296904","https://openalex.org/W2148349024","https://openalex.org/W2462901929","https://openalex.org/W2762278378","https://openalex.org/W2909062877","https://openalex.org/W2267038056","https://openalex.org/W2943568678","https://openalex.org/W2005067285","https://openalex.org/W2525526117","https://openalex.org/W2952719721","https://openalex.org/W3003760456","https://openalex.org/W2572546447","https://openalex.org/W3090563815","https://openalex.org/W2889631368","https://openalex.org/W2793130633","https://openalex.org/W2766301745","https://openalex.org/W2209990155","https://openalex.org/W3006447309","https://openalex.org/W2242801376"],"abstract_inverted_index":{"In":[0,54],"visual":[1],"recognition":[2],"tasks,":[3],"such":[4],"as":[5],"image":[6,100],"classification,":[7],"unsupervised":[8,35,113],"learning":[9,38],"exploits":[10],"cheap":[11],"unlabeled":[12],"data":[13],"and":[14,49,98,103],"can":[15],"help":[16],"to":[17],"solve":[18],"these":[19],"tasks":[20],"more":[21,39,66],"efficiently.":[22],"We":[23,42,89],"show":[24],"that":[25],"the":[26,74,94,108],"recursive":[27],"autoconvolution":[28],"operator,":[29],"adopted":[30],"from":[31],"physics,":[32],"boosts":[33],"existing":[34],"methods":[36],"by":[37,82],"discriminative":[40],"filters.":[41],"take":[43],"well":[44],"established":[45],"convolutional":[46],"neural":[47],"networks":[48,92],"train":[50],"their":[51],"filters":[52,85],"layer-wise.":[53],"addition,":[55],"based":[56],"on":[57,93],"previous":[58],"works":[59],"we":[60],"design":[61],"a":[62],"network":[63],"which":[64],"extracts":[65],"than":[67],"600k":[68],"features":[69],"per":[70],"sample,":[71],"but":[72],"with":[73],"total":[75],"number":[76],"of":[77,107],"trainable":[78],"parameters":[79],"greatly":[80],"reduced":[81],"introducing":[83],"shared":[84],"in":[86],"higher":[87],"layers.":[88],"evaluate":[90],"our":[91],"MNIST,":[95],"CIFAR-10,":[96],"CIFAR-100":[97],"STL-10":[99],"classification":[101],"benchmarks":[102],"report":[104],"several":[105],"state":[106],"art":[109],"results":[110],"among":[111],"other":[112],"methods.":[114]},"counts_by_year":[],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}