{"id":"https://openalex.org/W3158179522","doi":"https://doi.org/10.1109/ijcnn52387.2021.9534111","title":"Spatio-Temporal Pruning and Quantization for Low-latency Spiking Neural Networks","display_name":"Spatio-Temporal Pruning and Quantization for Low-latency Spiking Neural Networks","publication_year":2021,"publication_date":"2021-07-18","ids":{"openalex":"https://openalex.org/W3158179522","doi":"https://doi.org/10.1109/ijcnn52387.2021.9534111","mag":"3158179522"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn52387.2021.9534111","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9534111","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 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/2104.12528","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103217948","display_name":"Sayeed Shafayet Chowdhury","orcid":"https://orcid.org/0000-0001-9493-5074"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sayeed Shafayet Chowdhury","raw_affiliation_strings":["School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA","Purdue University,School of Electrical and Computer Engineering,West Lafayette,IN,USA,47905"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"Purdue University,School of Electrical and Computer Engineering,West Lafayette,IN,USA,47905","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066407038","display_name":"Isha Garg","orcid":"https://orcid.org/0000-0003-4702-9444"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Isha Garg","raw_affiliation_strings":["School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA","Purdue University,School of Electrical and Computer Engineering,West Lafayette,IN,USA,47905"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"Purdue University,School of Electrical and Computer Engineering,West Lafayette,IN,USA,47905","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031161187","display_name":"Kaushik Roy","orcid":"https://orcid.org/0009-0002-3375-2877"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kaushik Roy","raw_affiliation_strings":["School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA","PURDUE UNIVERSITY"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"PURDUE UNIVERSITY","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103217948"],"corresponding_institution_ids":["https://openalex.org/I219193219"],"apc_list":null,"apc_paid":null,"fwci":0.3033,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.5511963,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":1.0,"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/T10581","display_name":"Neural dynamics and brain function","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9983999729156494,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7534136772155762},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.5710266828536987},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.553623378276825},{"id":"https://openalex.org/keywords/spiking-neural-network","display_name":"Spiking neural network","score":0.5351489782333374},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5230199694633484},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5009493827819824},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47073614597320557},{"id":"https://openalex.org/keywords/backpropagation","display_name":"Backpropagation","score":0.4505019783973694},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4404718577861786},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.43492767214775085},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4281918406486511},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2853309214115143}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7534136772155762},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.5710266828536987},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.553623378276825},{"id":"https://openalex.org/C11731999","wikidata":"https://www.wikidata.org/wiki/Q9067355","display_name":"Spiking neural network","level":3,"score":0.5351489782333374},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5230199694633484},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5009493827819824},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47073614597320557},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.4505019783973694},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4404718577861786},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43492767214775085},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4281918406486511},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2853309214115143},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/ijcnn52387.2021.9534111","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9534111","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2104.12528","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.12528","pdf_url":"https://arxiv.org/pdf/2104.12528","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3158179522","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2104.12528","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.2104.12528","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2104.12528","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2104.12528","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.12528","pdf_url":"https://arxiv.org/pdf/2104.12528","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.9100000262260437,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306087","display_name":"Semiconductor Research Corporation","ror":"https://ror.org/047z4n946"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3158179522.pdf","grobid_xml":"https://content.openalex.org/works/W3158179522.grobid-xml"},"referenced_works_count":57,"referenced_works":["https://openalex.org/W101771737","https://openalex.org/W1621450212","https://openalex.org/W1645800954","https://openalex.org/W1798945469","https://openalex.org/W1999085092","https://openalex.org/W2006370340","https://openalex.org/W2020676607","https://openalex.org/W2127218421","https://openalex.org/W2163605009","https://openalex.org/W2233731247","https://openalex.org/W2314470091","https://openalex.org/W2319920447","https://openalex.org/W2541249978","https://openalex.org/W2621826044","https://openalex.org/W2751438535","https://openalex.org/W2775079417","https://openalex.org/W2806066966","https://openalex.org/W2897802248","https://openalex.org/W2904473220","https://openalex.org/W2914117107","https://openalex.org/W2940297489","https://openalex.org/W2963000224","https://openalex.org/W2963403868","https://openalex.org/W2963674932","https://openalex.org/W2963966976","https://openalex.org/W2964296416","https://openalex.org/W2964299589","https://openalex.org/W2964304804","https://openalex.org/W2964338223","https://openalex.org/W2982479999","https://openalex.org/W2984844508","https://openalex.org/W2986628237","https://openalex.org/W3004127093","https://openalex.org/W3023137363","https://openalex.org/W3023721287","https://openalex.org/W3035008388","https://openalex.org/W3037354233","https://openalex.org/W3089934672","https://openalex.org/W3092055689","https://openalex.org/W3093729901","https://openalex.org/W3121127024","https://openalex.org/W6638060716","https://openalex.org/W6677580257","https://openalex.org/W6678914141","https://openalex.org/W6684191040","https://openalex.org/W6689286705","https://openalex.org/W6700264148","https://openalex.org/W6725543821","https://openalex.org/W6739901393","https://openalex.org/W6743958420","https://openalex.org/W6745571336","https://openalex.org/W6749922295","https://openalex.org/W6769953725","https://openalex.org/W6771742384","https://openalex.org/W6777015856","https://openalex.org/W6779701982","https://openalex.org/W6783452861"],"related_works":["https://openalex.org/W3200038452","https://openalex.org/W3205331893","https://openalex.org/W2995289984","https://openalex.org/W2485907003","https://openalex.org/W3208074141","https://openalex.org/W3175674467","https://openalex.org/W3207102667","https://openalex.org/W3161407672","https://openalex.org/W2898927016","https://openalex.org/W3100731286","https://openalex.org/W3133996370","https://openalex.org/W3009319415","https://openalex.org/W3012743867","https://openalex.org/W3179996328","https://openalex.org/W2341732087","https://openalex.org/W3199910846","https://openalex.org/W3185114446","https://openalex.org/W3163244872","https://openalex.org/W2973029888","https://openalex.org/W3205392725"],"abstract_inverted_index":{"Spiking":[0],"Neural":[1],"Networks":[2],"(SNNs)":[3],"are":[4,138,201],"a":[5,20,52],"promising":[6],"alternative":[7],"to":[8,61,103,180,191,238],"traditional":[9],"deep":[10,195],"learning":[11,196],"methods":[12,38],"since":[13],"they":[14,184],"perform":[15,227],"event-driven":[16],"information":[17],"processing.":[18],"However,":[19],"major":[21],"drawback":[22],"of":[23,31,51,57,73,91,97,207],"SNNs":[24,32,161,214],"is":[25,79,127],"high":[26],"inference":[27,110,174],"latency.":[28],"The":[29,136,158,198],"efficiency":[30],"could":[33],"be":[34],"enhanced":[35],"using":[36,87,140,155],"compression":[37,56],"such":[39],"as":[40],"pruning":[41,72,78,126],"and":[42,70,114,146,153,164,169,230],"quantization.":[43,240],"Notably,":[44],"SNNs,":[45],"unlike":[46],"their":[47,192],"non-spiking":[48],"counterparts,":[49],"consist":[50],"temporal":[53,71,125],"dimension,":[54],"the":[55,83,92,98,116,132,149,205],"which":[58],"can":[59],"lead":[60],"latency":[62,113,178],"reduction.":[63],"In":[64],"this":[65],"paper,":[66],"we":[67,147,226],"propose":[68],"spatial":[69,77],"SNNs.":[74,182],"First,":[75],"structured":[76],"performed":[80,128],"by":[81,129,203],"determining":[82],"layer-wise":[84],"significant":[85],"dimensions":[86],"principal":[88],"component":[89],"analysis":[90],"average":[93],"accumulated":[94],"membrane":[95],"potential":[96],"neurons.":[99],"This":[100],"step":[101],"leads":[102],"10-14X":[104],"model":[105],"compression.":[106],"Additionally,":[107],"it":[108],"enables":[109],"with":[111,175,209],"lower":[112],"decreases":[115],"spike":[117],"count":[118],"per":[119,211],"inference.":[120],"To":[121],"further":[122],"reduce":[123],"latency,":[124],"gradually":[130],"reducing":[131],"timesteps":[133],"while":[134,172],"training.":[135],"networks":[137],"trained":[139],"surrogate":[141],"gradient":[142],"descent":[143],"based":[144],"backpropagation":[145],"validate":[148],"results":[150],"on":[151,167],"CIFAR10":[152,168],"CIFAR100,":[154,170],"VGG":[156],"architectures.":[157],"spatiotemporally":[159],"pruned":[160],"achieve":[162],"89.04%":[163],"66.4%":[165],"accuracy":[166],"respectively,":[171],"performing":[173],"3-30X":[176],"reduced":[177],"compared":[179,190],"state-of-the-art":[181],"Moreover,":[183],"require":[185],"8-14X":[186],"lesser":[187],"compute":[188],"energy":[189,199,210],"unpruned":[193],"standard":[194],"counterparts.":[197],"numbers":[200],"obtained":[202],"multiplying":[204],"number":[206],"operations":[208],"operation.":[212],"These":[213],"also":[215],"provide":[216],"1\u20134%":[217],"higher":[218],"robustness":[219],"against":[220],"Gaussian":[221],"noise":[222],"corrupted":[223],"inputs.":[224],"Furthermore,":[225],"weight":[228],"quantization":[229],"find":[231],"that":[232],"performance":[233],"remains":[234],"reasonably":[235],"stable":[236],"up":[237],"5-bit":[239]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}