{"id":"https://openalex.org/W3127765145","doi":null,"title":"A Deeper Look into Convolutions via Pruning.","display_name":"A Deeper Look into Convolutions via Pruning.","publication_year":2021,"publication_date":"2021-02-04","ids":{"openalex":"https://openalex.org/W3127765145","mag":"3127765145"},"language":"en","primary_location":{"id":"mag:3127765145","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2102.02804.pdf","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/pdf/2102.02804.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009474947","display_name":"\u0130lke \u00c7u\u011fu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"\u0130lke \u00c7u\u011fu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5076398399","display_name":"Emre Akba\u015f","orcid":"https://orcid.org/0000-0002-3760-6722","observed_orcids":["https://orcid.org/0000-0002-3760-6722"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Emre Akba\u015f","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-3760-6722","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":0,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9994999766349792,"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"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":9.999999747378752e-05,"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":9.999999747378752e-05,"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/convolutional-neural-network-pruning","display_name":"convolutional neural network pruning","score":0.8489999771118164},{"id":"https://openalex.org/keywords/resnet","display_name":"ResNet","score":0.6710000038146973},{"id":"https://openalex.org/keywords/weight-sharing","display_name":"parameter sharing","score":0.6100000143051147},{"id":"https://openalex.org/keywords/image-classification","display_name":"image classification","score":0.746999979019165},{"id":"https://openalex.org/keywords/cifar-10","display_name":"CIFAR-10","score":0.7239999771118164},{"id":"https://openalex.org/keywords/cifar-100","display_name":"CIFAR-100","score":0.996999979019165},{"id":"https://openalex.org/keywords/tiny-imagenet","display_name":"Tiny ImageNet","score":0.8519999980926514},{"id":"https://openalex.org/keywords/model-compression","display_name":"model compression","score":0.35199999809265137}],"concepts":[{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.7871631979942322},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7562624216079712},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.731124758720398},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.6283152103424072},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5683407187461853},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.55643230676651},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5263270735740662},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5207938551902771},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.49912500381469727},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.48084506392478943},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.4773806929588318},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34164339303970337},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3127765145","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2102.02804.pdf","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:3127765145","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2102.02804.pdf","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W197865394","https://openalex.org/W1522301498","https://openalex.org/W1677182931","https://openalex.org/W1836465849","https://openalex.org/W1902150074","https://openalex.org/W1903029394","https://openalex.org/W2040910278","https://openalex.org/W2060902339","https://openalex.org/W2072541188","https://openalex.org/W2117539524","https://openalex.org/W2123341385","https://openalex.org/W2125209769","https://openalex.org/W2147800946","https://openalex.org/W2156297475","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2551176409","https://openalex.org/W2554302513","https://openalex.org/W2593634001","https://openalex.org/W2612445135","https://openalex.org/W2707890836","https://openalex.org/W2727426218","https://openalex.org/W2785533664","https://openalex.org/W2785678896","https://openalex.org/W2785749378","https://openalex.org/W2786054724","https://openalex.org/W2797713747","https://openalex.org/W2883070812","https://openalex.org/W2894581376","https://openalex.org/W2924515500","https://openalex.org/W2928560789","https://openalex.org/W2950220847","https://openalex.org/W2952746978","https://openalex.org/W2962851801","https://openalex.org/W2963145730","https://openalex.org/W2963163009","https://openalex.org/W2963363373","https://openalex.org/W2963382930","https://openalex.org/W2963518130","https://openalex.org/W2963540976","https://openalex.org/W2964217527","https://openalex.org/W2964233199","https://openalex.org/W2964266063","https://openalex.org/W2964299589","https://openalex.org/W2966992648","https://openalex.org/W2989808579","https://openalex.org/W2994081359","https://openalex.org/W2995629810","https://openalex.org/W3009616221","https://openalex.org/W3118608800","https://openalex.org/W3173173537","https://openalex.org/W4394670654"],"related_works":["https://openalex.org/W4307001652","https://openalex.org/W3094624326","https://openalex.org/W3127078660","https://openalex.org/W2798678112","https://openalex.org/W4312513271","https://openalex.org/W2994266908","https://openalex.org/W4385248679","https://openalex.org/W2889287351","https://openalex.org/W7103649284","https://openalex.org/W2900011986"],"abstract_inverted_index":{"Convolutional":[0],"neural":[1,15,164],"networks":[2,16,165],"(CNNs)":[3],"are":[4,31],"able":[5],"to":[6,23,33,54,107,139,148],"attain":[7],"better":[8],"visual":[9],"recognition":[10,99,123],"performance":[11],"than":[12],"fully":[13],"connected":[14],"despite":[17],"having":[18],"much":[19],"less":[20],"parameters":[21],"due":[22],"their":[24],"parameter":[25],"sharing":[26],"principle.":[27],"Hence,":[28,125],"modern":[29],"architectures":[30],"designed":[32],"contain":[34],"a":[35,156],"very":[36],"small":[37,65],"number":[38,82],"of":[39,49,67,83,86,112,121,155,160],"fully-connected":[40,61],"layers,":[41],"often":[42],"at":[43],"the":[44,72,81,87,119,122,131,140,152,168],"end,":[45],"after":[46],"multiple":[47],"layers":[48,62],"convolutions.":[50],"It":[51],"is":[52,103,116],"interesting":[53],"observe":[55],"that":[56,115],"we":[57,129],"can":[58,89],"replace":[59],"large":[60],"with":[63],"relatively":[64],"groups":[66],"tiny":[68],"matrices":[69],"applied":[70],"on":[71,135,151],"entire":[73],"image.":[74],"Moreover,":[75],"although":[76],"this":[77,109,127],"strategy":[78],"already":[79],"reduces":[80],"parameters,":[84],"most":[85],"convolutions":[88],"be":[90],"eliminated":[91],"as":[92],"well,":[93],"without":[94],"suffering":[95],"any":[96],"loss":[97],"in":[98,126,137],"performance.":[100],"However,":[101],"there":[102],"no":[104],"solid":[105],"recipe":[106],"detect":[108],"hidden":[110],"subset":[111],"convolutional":[113],"neurons":[114],"responsible":[117],"for":[118,146,167],"majority":[120],"work.":[124],"work,":[128],"use":[130],"matrix":[132],"characteristics":[133],"based":[134],"eigenvalues":[136],"addition":[138],"classical":[141],"weight-based":[142],"importance":[143],"assignment":[144],"approach":[145],"pruning":[147],"shed":[149],"light":[150],"internal":[153],"mechanisms":[154],"widely":[157],"used":[158],"family":[159],"CNNs,":[161],"namely":[162],"residual":[163],"(ResNets),":[166],"image":[169],"classification":[170],"problem":[171],"using":[172],"CIFAR-10,":[173],"CIFAR-100":[174],"and":[175],"Tiny":[176],"ImageNet":[177],"datasets.":[178]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2021-02-15T00:00:00"}