{"id":"https://openalex.org/W2271936473","doi":null,"title":"Efficient mapping of the training of Convolutional Neural Networks to a CUDA-based cluster","display_name":"Efficient mapping of the training of Convolutional Neural Networks to a CUDA-based cluster","publication_year":2012,"publication_date":"2012-01-01","ids":{"openalex":"https://openalex.org/W2271936473","mag":"2271936473"},"language":"en","primary_location":{"id":"mag:2271936473","doi":null,"is_oa":false,"landing_page_url":"https://hgpu.org/?p=6830","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5005949396","display_name":"Jonatan Ward","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jonatan Ward","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Sergey Andreev","orcid":"https://orcid.org/0000-0001-9673-6423","observed_orcids":["https://orcid.org/0000-0001-9673-6423"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sergey Andreev","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-9673-6423","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010833300","display_name":"Francisco Jos\u00e9 Heredia","orcid":"https://orcid.org/0000-0002-3849-8284","observed_orcids":["https://orcid.org/0000-0002-3849-8284"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Francisco J. Heredia","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-3849-8284","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019998534","display_name":"Bogdan Lazar","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bogdan Lazar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5020304666","display_name":"Zlatka Manevska","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Zlatka Manevska","raw_affiliation_strings":["Eindhoven University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology","institution_ids":["https://openalex.org/I83019370"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9951000213623047,"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"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9951000213623047,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0026000000070780516,"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/T10320","display_name":"Neural Networks and Applications","score":0.0003000000142492354,"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/convolutional-neural-networks","display_name":"convolutional neural networks","score":0.9399999976158142},{"id":"https://openalex.org/keywords/gpu-clusters","display_name":"GPU clusters","score":0.42800000309944153},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.9449999928474426},{"id":"https://openalex.org/keywords/parallel-training","display_name":"parallel training","score":0.9010000228881836},{"id":"https://openalex.org/keywords/gradient-computation","display_name":"gradient computation","score":0.8740000128746033},{"id":"https://openalex.org/keywords/parallelism","display_name":"parallelism","score":0.5130000114440918},{"id":"https://openalex.org/keywords/training-performance","display_name":"training performance","score":0.5529999732971191}],"concepts":[{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.8286617994308472},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.8213489651679993},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8135596513748169},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5866116285324097},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.563160240650177},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5627294778823853},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4862017035484314},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.466930091381073},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4491432309150696},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4168590009212494},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3374534249305725},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10161200165748596},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2271936473","doi":null,"is_oa":false,"landing_page_url":"https://hgpu.org/?p=6830","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W77656806","https://openalex.org/W2112796928","https://openalex.org/W2134557905","https://openalex.org/W2147798584","https://openalex.org/W2154987621"],"related_works":["https://openalex.org/W7097794536","https://openalex.org/W1598866093","https://openalex.org/W2792508107","https://openalex.org/W2264044607","https://openalex.org/W1547840952","https://openalex.org/W7120111704","https://openalex.org/W3196921579","https://openalex.org/W1544811214","https://openalex.org/W1871372305","https://openalex.org/W2983101505"],"abstract_inverted_index":{"We":[0,18,30],"propose":[1,50],"a":[2,9,15,20,43,71],"method":[3],"to":[4,57],"parallelize":[5],"the":[6,24,27,32,63,82],"training":[7,40],"of":[8,26,34,53,65,73],"convolutional":[10],"neural":[11],"network":[12],"by":[13],"using":[14,35],"CUDA-based":[16],"cluster.":[17,83],"attain":[19],"substantial":[21],"increase":[22],"in":[23],"performance":[25,44],"algorithm":[28,56],"itself.":[29],"research":[31],"feasibility":[33],"batch":[36],"versus":[37],"online":[38],"mode":[39],"and":[41],"provide":[42],"comparison":[45],"between":[46],"them.":[47],"Furthermore,":[48],"we":[49,69],"an":[51,54],"implementation":[52],"alternative":[55],"compute":[58],"local":[59],"gradients":[60],"which":[61],"increases":[62],"level":[64],"parallelism.":[66],"To":[67],"conclude,":[68],"give":[70],"set":[72],"best":[74],"practices":[75],"for":[76],"implementing":[77],"Convolutional":[78],"Neural":[79],"Networks":[80],"on":[81]},"counts_by_year":[{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2016-06-24T00:00:00"}