{"id":"https://openalex.org/W4382658119","doi":"https://doi.org/10.1109/tetc.2023.3289778","title":"CANNON: Communication-Aware Sparse Neural Network Optimization","display_name":"CANNON: Communication-Aware Sparse Neural Network Optimization","publication_year":2023,"publication_date":"2023-06-30","ids":{"openalex":"https://openalex.org/W4382658119","doi":"https://doi.org/10.1109/tetc.2023.3289778"},"language":"en","primary_location":{"id":"doi:10.1109/tetc.2023.3289778","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tetc.2023.3289778","pdf_url":null,"source":{"id":"https://openalex.org/S2496326734","display_name":"IEEE Transactions on Emerging Topics in Computing","issn_l":"2168-6750","issn":["2168-6750","2376-4562"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Emerging Topics in Computing","raw_type":"journal-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/A5000360959","display_name":"A. Alper Goksoy","orcid":"https://orcid.org/0000-0001-8679-9842"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"A. Alper Goksoy","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Wisconsin-Madison, Madison, WI, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Wisconsin-Madison, Madison, WI, USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108578601","display_name":"Guihong Li","orcid":"https://orcid.org/0000-0001-8537-8632"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guihong Li","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Texas at Austin, Austin, TX, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043173800","display_name":"Sumit K. Mandal","orcid":"https://orcid.org/0000-0002-9294-1603"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sumit K. Mandal","raw_affiliation_strings":["Department of Computer Science and Automation, Indian Institute of Science, Bangalore, Karnataka, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Automation, Indian Institute of Science, Bangalore, Karnataka, India","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084255924","display_name":"\u00dcmit Y. Ogras","orcid":"https://orcid.org/0000-0002-5045-5535"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Umit Y. Ogras","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Wisconsin-Madison, Madison, WI, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Wisconsin-Madison, Madison, WI, USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036227385","display_name":"Radu M\u0103rculescu","orcid":"https://orcid.org/0000-0003-1826-7646"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Radu Marculescu","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Texas at Austin, Austin, TX, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5000360959"],"corresponding_institution_ids":["https://openalex.org/I135310074"],"apc_list":null,"apc_paid":null,"fwci":0.4011,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.59292894,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"11","issue":"4","first_page":"882","last_page":"894"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9995999932289124,"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":0.9995999932289124,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9954000115394592,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.9908000230789185,"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/computer-science","display_name":"Computer science","score":0.7380876541137695},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7024343609809875},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.594352126121521},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5124967098236084},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.50972980260849},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4856499433517456},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.47699955105781555},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.4152473211288452},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3912419378757477},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.38149136304855347},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12984555959701538},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09437334537506104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7380876541137695},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7024343609809875},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.594352126121521},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5124967098236084},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.50972980260849},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4856499433517456},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.47699955105781555},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.4152473211288452},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3912419378757477},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.38149136304855347},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12984555959701538},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09437334537506104},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tetc.2023.3289778","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tetc.2023.3289778","pdf_url":null,"source":{"id":"https://openalex.org/S2496326734","display_name":"IEEE Transactions on Emerging Topics in Computing","issn_l":"2168-6750","issn":["2168-6750","2376-4562"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Emerging Topics in Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.9100000262260437}],"awards":[{"id":"https://openalex.org/G3000405756","display_name":null,"funder_award_id":"GRC 2939.001","funder_id":"https://openalex.org/F4320306087","funder_display_name":"Semiconductor Research Corporation"},{"id":"https://openalex.org/G7209602845","display_name":null,"funder_award_id":"3012.001","funder_id":"https://openalex.org/F4320306087","funder_display_name":"Semiconductor Research Corporation"},{"id":"https://openalex.org/G7493855455","display_name":null,"funder_award_id":"CNS-2007284","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1563795667","https://openalex.org/W1686810756","https://openalex.org/W1935978687","https://openalex.org/W2008620264","https://openalex.org/W2112090702","https://openalex.org/W2118231264","https://openalex.org/W2126004407","https://openalex.org/W2156150815","https://openalex.org/W2194775991","https://openalex.org/W2245094585","https://openalex.org/W2276892413","https://openalex.org/W2551176409","https://openalex.org/W2613989746","https://openalex.org/W2782046614","https://openalex.org/W2808133870","https://openalex.org/W2809171749","https://openalex.org/W2883149906","https://openalex.org/W2910506572","https://openalex.org/W2949674408","https://openalex.org/W2979429416","https://openalex.org/W2982479999","https://openalex.org/W2985125066","https://openalex.org/W3005087657","https://openalex.org/W3005409765","https://openalex.org/W3035560939","https://openalex.org/W3048606948","https://openalex.org/W3091350994","https://openalex.org/W3091922395","https://openalex.org/W3094031577","https://openalex.org/W3118608800","https://openalex.org/W3145926676","https://openalex.org/W3167436278","https://openalex.org/W3184191382","https://openalex.org/W4243519499","https://openalex.org/W4244330903","https://openalex.org/W6633802082","https://openalex.org/W6637373629","https://openalex.org/W6677103964","https://openalex.org/W6732814185","https://openalex.org/W6751979845","https://openalex.org/W6770384565","https://openalex.org/W6787972765"],"related_works":["https://openalex.org/W2307385607","https://openalex.org/W4249307902","https://openalex.org/W2375742443","https://openalex.org/W2149381099","https://openalex.org/W4200520489","https://openalex.org/W1483190388","https://openalex.org/W2049400599","https://openalex.org/W2061536531","https://openalex.org/W193873054","https://openalex.org/W2049261842"],"abstract_inverted_index":{"Sparse":[0],"deep":[1],"neural":[2],"networks":[3],"(DNNs)":[4],"have":[5,40],"the":[6,31,51,62,94,98,101,107,121,128,168],"potential":[7,64],"to":[8,30,60,144,159],"deliver":[9],"compelling":[10],"performance":[11],"and":[12,75,110,140,153],"energy":[13],"efficiency":[14],"without":[15],"significant":[16,42],"accuracy":[17,170],"loss.":[18],"However,":[19],"their":[20,26],"benefits":[21],"can":[22,39],"quickly":[23],"diminish":[24],"if":[25,44],"training":[27,57],"is":[28,58],"oblivious":[29],"target":[32,52,102],"hardware.":[33,53],"For":[34],"example,":[35],"fewer":[36],"critical":[37],"connections":[38],"a":[41,73,135,164],"overhead":[43],"they":[45],"translate":[46],"into":[47],"long-distance":[48],"communication":[49,122,147,151],"on":[50,127,167,171],"Therefore,":[54],"hardware-aware":[55],"sparse":[56,66,78,115],"needed":[59],"leverage":[61],"full":[63],"of":[65,100,138],"DNNs.":[67],"To":[68],"this":[69],"end,":[70],"we":[71],"propose":[72],"novel":[74],"comprehensive":[76],"communication-aware":[77,114],"DNN":[79,95,129],"optimization":[80],"framework":[81],"for":[82],"tile-based":[83],"in-memory":[84],"computing":[85],"(IMC)":[86],"architectures.":[87],"The":[88],"proposed":[89],"technique,":[90],"CANNON":[91,119],"first":[92],"maps":[93],"layers":[96,112],"onto":[97],"tiles":[99],"architecture.":[103],"Then,":[104],"it":[105],"replaces":[106],"fully":[108],"connected":[109],"convolutional":[111],"with":[113,124,134,163],"connections.":[116],"After":[117],"that,":[118],"optimizes":[120],"cost":[123],"minimal":[125],"impact":[126,166],"accuracy.":[130],"Extensive":[131],"experimental":[132],"evaluations":[133],"wide":[136],"range":[137],"DNNs":[139],"datasets":[141],"show":[142],"up":[143],"3.0\u00d7":[145],"lower":[146,150,155],"energy,":[148],"3.1\u00d7":[149],"latency,":[152],"6.8\u00d7":[154],"energy-delay":[156],"product":[157],"compared":[158],"state-of-the-art":[160],"pruning":[161],"approaches":[162],"negligible":[165],"classification":[169],"IMC-based":[172],"machine":[173],"learning":[174],"accelerators.":[175]},"counts_by_year":[{"year":2024,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}