{"id":"https://openalex.org/W2798668634","doi":"https://doi.org/10.23919/date.2018.8342074","title":"NN compactor: Minimizing memory and logic resources for small neural networks","display_name":"NN compactor: Minimizing memory and logic resources for small neural networks","publication_year":2018,"publication_date":"2018-03-01","ids":{"openalex":"https://openalex.org/W2798668634","doi":"https://doi.org/10.23919/date.2018.8342074","mag":"2798668634"},"language":"en","primary_location":{"id":"doi:10.23919/date.2018.8342074","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date.2018.8342074","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Design, Automation & Test in Europe Conference & Exhibition (DATE)","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/A5075135160","display_name":"Seongmin Hong","orcid":"https://orcid.org/0000-0001-6904-8094"},"institutions":[{"id":"https://openalex.org/I94588446","display_name":"Hongik University","ror":"https://ror.org/00egdv862","country_code":"KR","type":"education","lineage":["https://openalex.org/I94588446"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Seongmin Hong","raw_affiliation_strings":["Dept. of Electronic and Electrical Engineering, Hongik University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Dept. of Electronic and Electrical Engineering, Hongik University, Seoul, Korea","institution_ids":["https://openalex.org/I94588446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101658391","display_name":"Inho Lee","orcid":"https://orcid.org/0000-0002-5046-5207"},"institutions":[{"id":"https://openalex.org/I94588446","display_name":"Hongik University","ror":"https://ror.org/00egdv862","country_code":"KR","type":"education","lineage":["https://openalex.org/I94588446"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Inho Lee","raw_affiliation_strings":["Dept. of Electronic and Electrical Engineering, Hongik University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Dept. of Electronic and Electrical Engineering, Hongik University, Seoul, Korea","institution_ids":["https://openalex.org/I94588446"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086980677","display_name":"Yongjun Park","orcid":"https://orcid.org/0000-0003-3725-0380"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yongjun Park","raw_affiliation_strings":["Dept. of Computer Science, Hanyang University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science, Hanyang University, Seoul, Korea","institution_ids":["https://openalex.org/I4575257"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5075135160"],"corresponding_institution_ids":["https://openalex.org/I94588446"],"apc_list":null,"apc_paid":null,"fwci":0.7111,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.73788857,"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":"581","last_page":"584"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":1.0,"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":1.0,"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/T12676","display_name":"Machine Learning and ELM","score":0.9983999729156494,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9972000122070312,"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":0.786800742149353},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6560254096984863},{"id":"https://openalex.org/keywords/mnist-database","display_name":"MNIST database","score":0.5645109415054321},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.5349043607711792},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.5063115358352661},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.47683897614479065},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.4559505581855774},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.43255865573883057},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.38391509652137756},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3624822497367859},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.307533860206604},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2474791705608368},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2284732460975647}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.786800742149353},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6560254096984863},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.5645109415054321},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.5349043607711792},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.5063115358352661},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.47683897614479065},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.4559505581855774},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.43255865573883057},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.38391509652137756},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3624822497367859},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.307533860206604},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2474791705608368},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2284732460975647},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/date.2018.8342074","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date.2018.8342074","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Design, Automation & Test in Europe Conference & Exhibition (DATE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8899999856948853,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1669276382","https://openalex.org/W1922655562","https://openalex.org/W2097117768","https://openalex.org/W2152839228","https://openalex.org/W2163605009","https://openalex.org/W2271840356","https://openalex.org/W2513554817","https://openalex.org/W2562773490","https://openalex.org/W4242577057","https://openalex.org/W4245199738","https://openalex.org/W6684191040"],"related_works":["https://openalex.org/W4386603768","https://openalex.org/W2950475743","https://openalex.org/W2886711096","https://openalex.org/W2750384547","https://openalex.org/W4380078352","https://openalex.org/W3204400881","https://openalex.org/W3214410901","https://openalex.org/W3204296682","https://openalex.org/W3183118997","https://openalex.org/W2917767146"],"abstract_inverted_index":{"Special":[0],"neural":[1,23,39,157,199],"accelerators":[2,24,40],"are":[3,30,56,138],"an":[4,202],"appealing":[5],"hardware":[6],"platform":[7],"for":[8,47],"machine":[9],"learning":[10],"systems":[11],"because":[12,37,64],"they":[13,29],"provide":[14],"both":[15],"high":[16,42],"performance":[17,204],"and":[18,45,134,170,191],"energy":[19],"efficiency.":[20],"Although":[21],"various":[22],"have":[25],"recently":[26],"been":[27],"introduced,":[28],"difficult":[31],"to":[32,34,59,93,102,113],"adapt":[33],"embedded":[35,211],"platforms":[36,55],"current":[38],"require":[41],"memory":[43,62,162],"capacity":[44],"bandwidth":[46],"the":[48,76,94,120,123,161,172,183],"fast":[49],"preparation":[50],"of":[51,65,73,97,122,164,175,188,206],"synaptic":[52,115,165],"weights.":[53],"Embedded":[54],"often":[57],"unable":[58],"meet":[60],"these":[61],"requirements":[63,163,174],"their":[66],"limited":[67],"resources.":[68],"In":[69,100,129,141],"FPGA-based":[70],"IoT":[71],"(internet":[72],"things)":[74],"systems,":[75],"problem":[77],"becomes":[78],"even":[79],"worse":[80],"since":[81],"computation":[82],"units":[83],"generated":[84],"from":[85],"logic":[86,173],"blocks":[87],"cannot":[88],"be":[89],"fully":[90,147],"utilized":[91],"due":[92],"small":[95,135],"size":[96],"block":[98],"memory.":[99],"order":[101],"overcome":[103],"this":[104,130,142],"problem,":[105],"we":[106,144],"propose":[107],"a":[108,146,155,209],"novel":[109],"dual-track":[110,168],"quantization":[111,169],"technique":[112],"reduce":[114],"weight":[116],"width":[117],"based":[118],"on":[119],"magnitude":[121],"value":[124,136],"while":[125],"minimizing":[126,160,171],"accuracy":[127,180,218],"loss.":[128,181,219],"value-adaptive":[131],"technique,":[132],"large":[133],"weights":[137,166],"quantized":[139],"differently.":[140],"paper,":[143],"present":[145],"automatic":[148],"framework":[149],"called":[150],"NN":[151],"Compactor":[152],"that":[153,196],"generates":[154],"compact":[156,198],"accelerator":[158,200],"by":[159],"through":[167],"PUs":[176],"with":[177,216],"minimum":[178],"recognition":[179],"For":[182],"three":[184],"widely":[185],"used":[186],"datasets":[187],"MNIST,":[189],"CNAE-9,":[190],"Forest,":[192],"experimental":[193],"results":[194],"demonstrate":[195],"our":[197],"achieves":[201],"average":[203],"improvement":[205],"6.4\u03c7":[207],"over":[208],"baseline":[210],"system":[212],"using":[213],"minimal":[214,217],"resources":[215]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}