{"id":"https://openalex.org/W2789613043","doi":"https://doi.org/10.1109/globalsip.2017.8309176","title":"Activation pruning of deep convolutional neural networks","display_name":"Activation pruning of deep convolutional neural networks","publication_year":2017,"publication_date":"2017-11-01","ids":{"openalex":"https://openalex.org/W2789613043","doi":"https://doi.org/10.1109/globalsip.2017.8309176","mag":"2789613043"},"language":"en","primary_location":{"id":"doi:10.1109/globalsip.2017.8309176","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globalsip.2017.8309176","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Global Conference on Signal and Information Processing (GlobalSIP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064497251","display_name":"Arash Ardakani","orcid":"https://orcid.org/0000-0003-3274-2394"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Arash Ardakani","raw_affiliation_strings":["Department of Electrical and Computer Engineering, McGill University, Montreal, QC, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, McGill University, Montreal, QC, Canada","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085812448","display_name":"Carlo Condo","orcid":"https://orcid.org/0000-0002-3050-036X"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Carlo Condo","raw_affiliation_strings":["Department of Electrical and Computer Engineering, McGill University, Montreal, QC, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, McGill University, Montreal, QC, Canada","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091600002","display_name":"Warren J. Gross","orcid":"https://orcid.org/0000-0002-6226-6037"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Warren J. Gross","raw_affiliation_strings":["Department of Electrical and Computer Engineering, McGill University, Montreal, QC, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, McGill University, Montreal, QC, Canada","institution_ids":["https://openalex.org/I5023651"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5064497251"],"corresponding_institution_ids":["https://openalex.org/I5023651"],"apc_list":null,"apc_paid":null,"fwci":0.6372,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.79366062,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1325","last_page":"1329"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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":0.9998000264167786,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.998199999332428,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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":0.8604400157928467},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.7849261164665222},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7379087805747986},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.7125875949859619},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.706693172454834},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5840638279914856},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5654700398445129},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5208680629730225},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.43080365657806396},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3721526265144348},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08304759860038757}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8604400157928467},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.7849261164665222},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7379087805747986},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.7125875949859619},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.706693172454834},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5840638279914856},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5654700398445129},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5208680629730225},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.43080365657806396},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3721526265144348},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08304759860038757},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/globalsip.2017.8309176","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globalsip.2017.8309176","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Global Conference on Signal and Information Processing (GlobalSIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W137941959","https://openalex.org/W825525975","https://openalex.org/W1604973310","https://openalex.org/W1686810756","https://openalex.org/W1902934009","https://openalex.org/W2147800946","https://openalex.org/W2219959730","https://openalex.org/W2285660444","https://openalex.org/W2289252105","https://openalex.org/W2384495648","https://openalex.org/W2550815077","https://openalex.org/W2563740559","https://openalex.org/W2565960208","https://openalex.org/W2597215741","https://openalex.org/W2919115771","https://openalex.org/W2950656546","https://openalex.org/W2962835968","https://openalex.org/W2963000224","https://openalex.org/W2963114950","https://openalex.org/W2963200642","https://openalex.org/W2963671426","https://openalex.org/W2963674932","https://openalex.org/W2964200805","https://openalex.org/W3024621361","https://openalex.org/W3207342693","https://openalex.org/W6623178044","https://openalex.org/W6637373629","https://openalex.org/W6638632666","https://openalex.org/W6639703010","https://openalex.org/W6687785706","https://openalex.org/W6725543821","https://openalex.org/W6729256011"],"related_works":["https://openalex.org/W2120447654","https://openalex.org/W2977179488","https://openalex.org/W2144453115","https://openalex.org/W2128223750","https://openalex.org/W4238532390","https://openalex.org/W2188872161","https://openalex.org/W2961779879","https://openalex.org/W797688974","https://openalex.org/W2002978035","https://openalex.org/W2209382646"],"abstract_inverted_index":{"Deep":[0],"neural":[1],"networks":[2,79,110,122,128],"(DNNs)":[3],"have":[4],"risen":[5],"to":[6,14,45,92,106],"prominence,":[7],"in":[8,53,129],"the":[9,34,37,47,63,94,107,112,120,126],"last":[10],"few":[11],"years,":[12],"thanks":[13],"their":[15,26],"very":[16],"good":[17],"performance":[18],"on":[19],"different":[20],"classification":[21],"and":[22,52,77],"recognition":[23],"tasks.":[24],"However,":[25],"implementations":[27,42],"suffer":[28],"from":[29],"long":[30],"latency":[31],"caused":[32],"by":[33],"complexity":[35],"of":[36,50,55,66,83,96,115,131],"network.":[38],"Recently,":[39],"many":[40],"hardware":[41],"were":[43],"introduced":[44],"accelerate":[46],"processing":[48],"time":[49],"DNNs,":[51],"particular":[54],"convolutional":[56,98],"layers.":[57],"While":[58],"they":[59],"can":[60],"easily":[61],"meet":[62],"timing":[64],"constraint":[65],"real-time":[67],"applications":[68],"for":[69],"small":[70],"networks,":[71],"complex":[72],"models":[73],"such":[74],"as":[75],"VGG":[76],"VGG-like":[78],"are":[80],"still":[81],"out":[82],"reach.":[84],"In":[85],"this":[86],"paper,":[87],"we":[88,117],"propose":[89],"an":[90],"technique":[91],"prune":[93],"neurons":[95],"each":[97],"layer,":[99],"also":[100],"called":[101],"activations,":[102,116],"which":[103],"directly":[104],"contribute":[105],"latency.":[108],"Comparing":[109],"with":[111],"same":[113],"number":[114],"show":[118],"that":[119],"activation-pruned":[121],"perform":[123],"better":[124],"than":[125],"unpruned":[127],"terms":[130],"misclassification":[132],"error.":[133]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2}],"updated_date":"2025-11-25T21:42:39.735039","created_date":"2025-10-10T00:00:00"}