{"id":"https://openalex.org/W3011962058","doi":"https://doi.org/10.1109/southeastcon42311.2019.9020427","title":"A Novel Approach Using MPI to Reduce Training Time for Capsule Networks","display_name":"A Novel Approach Using MPI to Reduce Training Time for Capsule Networks","publication_year":2019,"publication_date":"2019-04-01","ids":{"openalex":"https://openalex.org/W3011962058","doi":"https://doi.org/10.1109/southeastcon42311.2019.9020427","mag":"3011962058"},"language":"en","primary_location":{"id":"doi:10.1109/southeastcon42311.2019.9020427","doi":"https://doi.org/10.1109/southeastcon42311.2019.9020427","is_oa":false,"landing_page_url":"https://doi.org/10.1109/southeastcon42311.2019.9020427","pdf_url":null,"source":{"id":"https://openalex.org/S4393917016","display_name":"IEEE SoutheastCon","issn_l":"1091-0050","issn":["1091-0050"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 SoutheastCon","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","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":null,"display_name":"David Schwab","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I177097968","display_name":"University of Tennessee at Chattanooga","ror":"https://ror.org/00nqb1v70","country_code":"US","type":"education","lineage":["https://openalex.org/I177097968"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Schwab","raw_affiliation_strings":["College of Engineering and Computer Science University of Tennessee at Chattanooga Chattanooga, TN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Engineering and Computer Science University of Tennessee at Chattanooga Chattanooga, TN, USA","institution_ids":["https://openalex.org/I177097968"]}]},{"author_position":"last","author":{"id":null,"display_name":"Li Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I177097968","display_name":"University of Tennessee at Chattanooga","ror":"https://ror.org/00nqb1v70","country_code":"US","type":"education","lineage":["https://openalex.org/I177097968"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li Yang","raw_affiliation_strings":["College of Engineering and Computer Science University of Tennessee at Chattanooga Chattanooga, TN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Engineering and Computer Science University of Tennessee at Chattanooga Chattanooga, TN, USA","institution_ids":["https://openalex.org/I177097968"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I177097968"],"apc_list":null,"apc_paid":null,"fwci":0.163,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.54593656,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.7139000296592712,"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":0.7139000296592712,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.15710000693798065,"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"}},{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.019300000742077827,"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/capsule-networks","display_name":"capsule networks","score":1.0},{"id":"https://openalex.org/keywords/training-time-reduction","display_name":"training time reduction","score":0.843999981880188},{"id":"https://openalex.org/keywords/mpi","display_name":"MPI","score":0.6299999952316284},{"id":"https://openalex.org/keywords/distributed-training","display_name":"distributed training","score":0.828000009059906},{"id":"https://openalex.org/keywords/cluster-computing","display_name":"cluster computing","score":0.6779999732971191},{"id":"https://openalex.org/keywords/ensemble-voting","display_name":"ensemble voting","score":0.6320000290870667},{"id":"https://openalex.org/keywords/object-classification","display_name":"object classification","score":0.5600000023841858},{"id":"https://openalex.org/keywords/orientation-invariance","display_name":"orientation invariance","score":0.6790000200271606},{"id":"https://openalex.org/keywords/data-efficient-training","display_name":"data-efficient training","score":0.45899999141693115}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.833838701248169},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6761431097984314},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5911475419998169},{"id":"https://openalex.org/C2778778583","wikidata":"https://www.wikidata.org/wiki/Q147768","display_name":"Capsule","level":2,"score":0.5787176489830017},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5548890829086304},{"id":"https://openalex.org/C2777526511","wikidata":"https://www.wikidata.org/wiki/Q691543","display_name":"Pace","level":2,"score":0.5544530153274536},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.545669674873352},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5247359871864319},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.5076695680618286},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.41332268714904785},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38723224401474},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37888383865356445},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/southeastcon42311.2019.9020427","doi":"https://doi.org/10.1109/southeastcon42311.2019.9020427","is_oa":false,"landing_page_url":"https://doi.org/10.1109/southeastcon42311.2019.9020427","pdf_url":null,"source":{"id":"https://openalex.org/S4393917016","display_name":"IEEE SoutheastCon","issn_l":"1091-0050","issn":["1091-0050"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 SoutheastCon","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/9","score":0.4099999964237213,"display_name":"Industry, innovation and infrastructure"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2141125852","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2546302380","https://openalex.org/W2751777443","https://openalex.org/W2785994986","https://openalex.org/W2900594532","https://openalex.org/W2901285161","https://openalex.org/W2905175929","https://openalex.org/W2912277744","https://openalex.org/W2963446712"],"related_works":["https://openalex.org/W2947430673","https://openalex.org/W6891832492","https://openalex.org/W2996417370","https://openalex.org/W4402567071","https://openalex.org/W3159351747","https://openalex.org/W4388852589","https://openalex.org/W3200615055","https://openalex.org/W3089452734","https://openalex.org/W4327862077","https://openalex.org/W4404853496"],"abstract_inverted_index":{"The":[0],"deep":[1,39],"learning":[2,40],"environment":[3,140],"is":[4,28,33],"currently":[5],"developing":[6],"at":[7,67,75],"an":[8,108],"exciting":[9],"pace":[10],"as":[11,62],"new":[12,15,22,26,36],"techniques":[13],"and":[14,64,141],"results":[16,151],"are":[17,49,73],"consistently":[18],"being":[19],"released":[20],"through":[21],"research.":[23],"One":[24],"such":[25],"development":[27],"the":[29,42,80,83,115,131,155],"capsule":[30,119],"network":[31,48],"which":[32],"a":[34,46,86,138],"novel":[35],"approach":[37],"to":[38,113,144,147,152],"wherein":[41,110],"standard":[43],"neurons":[44,56],"of":[45,79,82,118],"neural":[47,100],"replaced":[50],"with":[51],"capsules.":[52],"Capsules":[53],"differ":[54],"from":[55],"in":[57,85,137],"that":[58],"they":[59],"receive":[60],"vectors":[61,66],"input":[63],"create":[65],"their":[68,149],"output.":[69],"Capsule":[70,89],"networks":[71,90,101],"additionally":[72],"good":[74],"classifying":[76],"objects":[77],"irrelative":[78],"orientation":[81],"object":[84],"given":[87],"image.":[88,160],"can":[91],"also":[92],"train":[93],"on":[94,154],"less":[95],"data":[96],"than":[97],"traditional":[98],"convolutional":[99],"(CNNs).":[102],"In":[103],"this":[104,128],"paper":[105],"we":[106,111],"present":[107],"experiment":[109],"aim":[112],"reduce":[114],"training":[116,132],"time":[117],"networks,":[120],"while":[121],"still":[122],"retaining":[123],"acceptable":[124],"accuracy.":[125],"We":[126],"accomplish":[127],"by":[129],"dividing":[130],"set":[133],"among":[134],"multiple":[135],"nodes":[136,146],"cluster":[139],"using":[142],"MPI":[143],"allow":[145],"communicate":[148],"classification":[150,157],"vote":[153],"correct":[156],"for":[158],"each":[159]},"counts_by_year":[{"year":2021,"cited_by_count":2}],"updated_date":"2026-10-26T11:51:55.731654","created_date":"2020-03-23T00:00:00"}