{"id":"https://openalex.org/W2905184098","doi":"https://doi.org/10.1109/jetcas.2018.2865006","title":"Mosaic-CNN: A Combined Two-Step Zero Prediction Approach to Trade off Accuracy and Computation Energy in Convolutional Neural Networks","display_name":"Mosaic-CNN: A Combined Two-Step Zero Prediction Approach to Trade off Accuracy and Computation Energy in Convolutional Neural Networks","publication_year":2018,"publication_date":"2018-08-13","ids":{"openalex":"https://openalex.org/W2905184098","doi":"https://doi.org/10.1109/jetcas.2018.2865006","mag":"2905184098"},"language":"en","primary_location":{"id":"doi:10.1109/jetcas.2018.2865006","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jetcas.2018.2865006","pdf_url":null,"source":{"id":"https://openalex.org/S142323794","display_name":"IEEE Journal on Emerging and Selected Topics in Circuits and Systems","issn_l":"2156-3357","issn":["2156-3357","2156-3365"],"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 Journal on Emerging and Selected Topics in Circuits and Systems","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/A5091666601","display_name":"Cheolhwan Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Cheolhwan Kim","raw_affiliation_strings":["School of Electrical Engineering, Korea University, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Korea University, Seoul, South Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091058036","display_name":"Dongyeob Shin","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dongyeob Shin","raw_affiliation_strings":["DRAM Design Team, Samsung Electronics Inc., Hwaseong, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DRAM Design Team, Samsung Electronics Inc., Hwaseong, South Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048187093","display_name":"Bohun Kim","orcid":"https://orcid.org/0000-0003-2858-571X"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Bohun Kim","raw_affiliation_strings":["DRAM Design Team, Samsung Electronics Inc., Hwaseong, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DRAM Design Team, Samsung Electronics Inc., Hwaseong, South Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101839916","display_name":"Jongsun Park","orcid":"https://orcid.org/0000-0003-3251-0024"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jongsun Park","raw_affiliation_strings":["DRAM Design Team, Samsung Electronics Inc., Hwaseong, South Korea"],"raw_orcid":"https://orcid.org/0000-0003-3251-0024","affiliations":[{"raw_affiliation_string":"DRAM Design Team, Samsung Electronics Inc., Hwaseong, South Korea","institution_ids":["https://openalex.org/I2250650973"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7283,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.77362767,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"8","issue":"4","first_page":"770","last_page":"781"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9995999932289124,"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":0.9990000128746033,"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/convolutional-neural-network","display_name":"Convolutional neural network","score":0.8649166822433472},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.8236879706382751},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.732833743095398},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6680005788803101},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5085541009902954},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.49364861845970154},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.45929163694381714},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43763548135757446},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39546313881874084},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.33998894691467285},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.30471792817115784},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21053194999694824},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08167743682861328}],"concepts":[{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.8649166822433472},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.8236879706382751},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.732833743095398},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6680005788803101},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5085541009902954},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.49364861845970154},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.45929163694381714},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43763548135757446},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39546313881874084},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.33998894691467285},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.30471792817115784},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21053194999694824},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08167743682861328}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jetcas.2018.2865006","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jetcas.2018.2865006","pdf_url":null,"source":{"id":"https://openalex.org/S142323794","display_name":"IEEE Journal on Emerging and Selected Topics in Circuits and Systems","issn_l":"2156-3357","issn":["2156-3357","2156-3365"],"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 Journal on Emerging and Selected Topics in Circuits and Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.9100000262260437}],"awards":[{"id":"https://openalex.org/G7565781445","display_name":null,"funder_award_id":"NRF-2016R1A2B4015329","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G8495113846","display_name":null,"funder_award_id":"10077445","funder_id":"https://openalex.org/F4320334879","funder_display_name":"Korea Evaluation Institute of Industrial Technology"}],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320334879","display_name":"Korea Evaluation Institute of Industrial Technology","ror":"https://ror.org/03z9cwa38"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2119144962","https://openalex.org/W2163605009","https://openalex.org/W2271840356","https://openalex.org/W2289252105","https://openalex.org/W2516141709","https://openalex.org/W2565960208","https://openalex.org/W2605487586","https://openalex.org/W2612076670","https://openalex.org/W2613119772","https://openalex.org/W2625457103","https://openalex.org/W2759777444","https://openalex.org/W2963674932","https://openalex.org/W2964299589","https://openalex.org/W4246219036","https://openalex.org/W6620707391","https://openalex.org/W6677580257","https://openalex.org/W6684191040","https://openalex.org/W6737910693"],"related_works":["https://openalex.org/W2317245370","https://openalex.org/W4249323025","https://openalex.org/W198851386","https://openalex.org/W2030310580","https://openalex.org/W947442053","https://openalex.org/W1980160788","https://openalex.org/W2148915962","https://openalex.org/W2283866686","https://openalex.org/W2319266294","https://openalex.org/W4287182096"],"abstract_inverted_index":{"In":[0,37,77,118],"convolutional":[1,5,85],"neural":[2],"networks":[3],"(CNNs),":[4],"layers":[6],"consume":[7],"dominant":[8],"portion":[9],"of":[10,17,83,101,116],"computation":[11,73,111,134],"energy":[12,74,112,181],"due":[13],"to":[14,45,109,120,186],"large":[15],"amount":[16],"multiply-accumulate":[18],"operations":[19],"(MACs).":[20],"However,":[21],"those":[22],"MACs":[23],"become":[24,35],"meaningless":[25],"(zeroes)":[26],"after":[27],"rectified":[28],"linear":[29],"unit":[30],"when":[31],"the":[32,49,78,81,99,114,123,145,153,161,172,175,193],"convolution":[33],"results":[34,167],"negative.":[36],"this":[38],"paper,":[39],"we":[40,125],"present":[41],"an":[42,94],"efficient":[43],"approach":[44],"predict":[46],"and":[47],"skip":[48],"convolutions":[50],"generating":[51],"zero":[52,57],"outputs.":[53],"The":[54,149,165],"proposed":[55,176],"two-step":[56],"prediction":[58],"approach,":[59],"called":[60],"mosaic":[61,79],"CNN,":[62,80],"can":[63,106,179],"be":[64,107],"effectively":[65],"used":[66],"for":[67,72,188],"trading":[68],"off":[69],"classification":[70,194],"accuracy":[71],"in":[75,93],"CNN.":[76],"outputs":[82],"each":[84],"layer":[86],"are":[87],"computed":[88],"considering":[89],"their":[90],"spatial":[91,102],"surroundings":[92,103],"output":[95],"feature":[96],"map.":[97],"Here,":[98],"types":[100],"(mosaic":[104],"types)":[105],"selected":[108],"save":[110,122],"at":[113],"expense":[115],"accuracy.":[117,195],"order":[119],"further":[121],"computations,":[124],"also":[126],"propose":[127],"a":[128,137],"most":[129],"significant":[130,142],"bits":[131,143],"(MSBs)":[132],"only":[133,147],"scheme,":[135],"where":[136],"constant":[138],"value":[139],"representing":[140],"least":[141],"compensates":[144],"MSBs":[146],"computations.":[148],"CNN":[150],"accelerator":[151,178],"supporting":[152],"combined":[154],"two":[155],"approaches":[156],"has":[157],"been":[158],"implemented":[159],"using":[160],"65-nm":[162],"CMOS":[163],"process.":[164],"numerical":[166],"show":[168],"that":[169],"compared":[170],"with":[171],"state-of-art":[173],"processor,":[174],"reconfigurable":[177],"achieve":[180],"savings":[182],"ranging":[183],"from":[184],"16.99%":[185],"29.64%":[187],"VGG-16":[189],"without":[190],"seriously":[191],"compromising":[192]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}