{"id":"https://openalex.org/W2203592760","doi":"https://doi.org/10.12677/csa.2015.512056","title":"The Influence of the Amount of Parameters in Different Layers on the Performance of Deep Learning Models","display_name":"The Influence of the Amount of Parameters in Different Layers on the Performance of Deep Learning Models","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2203592760","doi":"https://doi.org/10.12677/csa.2015.512056","mag":"2203592760"},"language":"en","primary_location":{"id":"doi:10.12677/csa.2015.512056","doi":"https://doi.org/10.12677/csa.2015.512056","is_oa":false,"landing_page_url":"https://doi.org/10.12677/csa.2015.512056","pdf_url":null,"source":{"id":"https://openalex.org/S2764804224","display_name":"Computer Science and Application","issn_l":"2161-8801","issn":["2161-8801","2161-881X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4322697029","host_organization_name":"Hans Publishers","host_organization_lineage":["https://openalex.org/P4322697029"],"host_organization_lineage_names":["Hans Publishers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Science and Application","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"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/A5008773910","display_name":"\u559c\u658c \u5cb3","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"\u559c\u658c \u5cb3","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5008773910"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":96},"biblio":{"volume":"05","issue":"12","first_page":"445","last_page":"453"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9926999807357788,"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":0.9926999807357788,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.004000000189989805,"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/T10320","display_name":"Neural Networks and Applications","score":0.0010000000474974513,"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":0.7739999890327454},{"id":"https://openalex.org/keywords/recurrent-convolutional-neural-network","display_name":"recurrent convolutional neural network","score":0.9819999933242798},{"id":"https://openalex.org/keywords/network-structure-design","display_name":"network structure design","score":0.7289999723434448},{"id":"https://openalex.org/keywords/image-classification","display_name":"image classification","score":0.7120000123977661},{"id":"https://openalex.org/keywords/cifar-10","display_name":"CIFAR-10","score":0.9549999833106995},{"id":"https://openalex.org/keywords/cifar-100","display_name":"CIFAR-100","score":1.0},{"id":"https://openalex.org/keywords/svhn","display_name":"SVHN","score":0.843999981880188}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.671954870223999},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43206924200057983}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.12677/csa.2015.512056","doi":"https://doi.org/10.12677/csa.2015.512056","is_oa":false,"landing_page_url":"https://doi.org/10.12677/csa.2015.512056","pdf_url":null,"source":{"id":"https://openalex.org/S2764804224","display_name":"Computer Science and Application","issn_l":"2161-8801","issn":["2161-8801","2161-881X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4322697029","host_organization_name":"Hans Publishers","host_organization_lineage":["https://openalex.org/P4322697029"],"host_organization_lineage_names":["Hans Publishers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Science and Application","raw_type":"journal-article"},{"id":"mag:2497799281","doi":null,"is_oa":false,"landing_page_url":"https://image.hanspub.org:8080/pdf/CSA20151200000_79830787.pdf","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W1799366690","https://openalex.org/W1921523184","https://openalex.org/W1934184906","https://openalex.org/W1981276685","https://openalex.org/W1993533483","https://openalex.org/W2097117768","https://openalex.org/W2147800946","https://openalex.org/W2154579312","https://openalex.org/W2163605009","https://openalex.org/W2168894214","https://openalex.org/W2186025005","https://openalex.org/W2294059674","https://openalex.org/W2595840341","https://openalex.org/W2950179405","https://openalex.org/W2963173190","https://openalex.org/W2963911037","https://openalex.org/W3037950864","https://openalex.org/W4394643672"],"related_works":["https://openalex.org/W2167343029","https://openalex.org/W2976014916","https://openalex.org/W2966554828","https://openalex.org/W7047442242","https://openalex.org/W3178964295","https://openalex.org/W4387987579","https://openalex.org/W7013044357","https://openalex.org/W4385759021","https://openalex.org/W2512245234","https://openalex.org/W3182611303"],"abstract_inverted_index":{"\u8fd1\u5e74\u6765\u6df1\u5ea6\u5b66\u4e60\u5728\u56fe\u50cf\u8bc6\u522b\u3001\u8bed\u97f3\u8bc6\u522b\u7b49\u9886\u57df\u5f97\u5230\u4e86\u5e7f\u6cdb\u7684\u5e94\u7528\uff0c\u53d6\u5f97\u4e86\u4f18\u5f02\u7684\u6548\u679c\uff0c\u4f46\u6df1\u5ea6\u5b66\u4e60\u7f51\u7edc\u7684\u7ed3\u6784\u8bbe\u8ba1\u6ca1\u6709\u4e00\u822c\u89c4\u5f8b\u53ef\u5faa\u3002\u672c\u6587\u57fa\u4e8e\u5377\u79ef\u795e\u7ecf\u7f51\u7edc\u548c\u9012\u5f52\u5377\u79ef\u795e\u7ecf\u7f51\u7edc\u6a21\u578b\u63a2\u7a76\u4e86\u6df1\u5ea6\u5b66\u4e60\u7f51\u7edc\u4e0d\u540c\u5c42\u7ea7\u95f4\u53c2\u6570\u5206\u5e03\u5bf9\u7f51\u7edc\u6027\u80fd\u7684\u5f71\u54cd\uff0c\u5728CIFAR-10\u3001CIFAR-100\u548cSVHN\u6570\u636e\u96c6\u4e0a\u8fdb\u884c\u4e86\u5927\u91cf\u7684\u5b9e\u9a8c\u3002\u7ed3\u679c\u8868\u660e\uff1a\u5728\u4fdd\u8bc1\u7f51\u7edc\u603b\u53c2\u6570\u5927\u81f4\u76f8\u7b49\u5e76\u7a33\u5b9a\u5728\u9971\u548c\u7684\u4e34\u754c\u503c\u9644\u8fd1\u7684\u6761\u4ef6\u4e0b\uff0c\u589e\u52a0\u9ad8\u5c42\u53c2\u6570\u6570\u91cf\u7684\u80fd\u591f\u63d0\u5347\u7f51\u7edc\u6027\u80fd\uff0c\u800c\u589e\u52a0\u4f4e\u5c42\u53c2\u6570\u6570\u91cf\u7684\u4f1a\u964d\u4f4e\u7f51\u7edc\u6027\u80fd\u3002\u901a\u8fc7\u8fd9\u4e00\u7b80\u5355\u7684\u89c4\u5219\uff0c\u6211\u4eec\u8bbe\u8ba1\u7684\u9012\u5f52\u5377\u79ef\u795e\u7ecf\u7f51\u7edc\u6a21\u578b\u7ed3\u6784\u5728CIFAR-100\u548cSVHN\u4e24\u4e2a\u6570\u636e\u96c6\u4e0a\u8fbe\u5230\u4e86\u76ee\u524d\u5355\u6a21\u578b\u6700\u4f4e\u7684\u8bc6\u522b\u9519\u8bef\u7387\u3002":[0],"In":[1],"recent":[2],"years,":[3],"deep":[4,50],"learning":[5,51],"has":[6],"been":[7],"widely":[8],"used":[9],"in":[10,45,87,103],"many":[11],"pattern":[12],"recognition":[13,20],"tasks":[14],"including":[15],"image":[16],"classification":[17,124],"and":[18,57,70,128],"speech":[19],"due":[21],"to":[22,109],"its":[23],"excellent":[24],"performance.":[25],"But":[26],"a":[27],"general":[28],"rule":[29],"for":[30],"the":[31,38,41,75,83,92,95,99,110,113,122],"structure":[32],"design":[33],"is":[34],"lacked.":[35],"We":[36],"explored":[37],"influence":[39],"of":[40,43,48,78,85,94,101,112],"amount":[42],"parameters":[44,79,86,102],"different":[46],"layers":[47,89,105],"two":[49],"models,":[52],"convolutional":[53,59],"neural":[54,60],"network":[55,61],"(CNN)":[56],"recurrent":[58],"(RCNN).":[62],"Experiments":[63],"on":[64,116,126],"three":[65],"benchmark":[66],"datasets,":[67],"CIFAR-10,":[68],"CIFAR-100":[69,127],"SVHN":[71,129],"showed":[72],"that":[73],"when":[74],"total":[76],"number":[77,84,100],"was":[80],"fixed,":[81],"increasing":[82,98],"higher":[88],"could":[90,106],"boost":[91],"performance":[93,111],"models":[96],"while":[97],"lower":[104],"be":[107],"harmful":[108],"models.":[114,132],"Based":[115],"this":[117],"simple":[118],"rule,":[119],"we":[120],"obtained":[121],"state-of-the-art":[123],"accuracy":[125],"with":[130],"single":[131]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}