{"id":"https://openalex.org/W3014069432","doi":"https://doi.org/10.1145/3373509.3373510","title":"A Reparameterized Construction in L2-Norm Weight Decay for Rectifier Neural Networks","display_name":"A Reparameterized Construction in L2-Norm Weight Decay for Rectifier Neural Networks","publication_year":2019,"publication_date":"2019-10-23","ids":{"openalex":"https://openalex.org/W3014069432","doi":"https://doi.org/10.1145/3373509.3373510","mag":"3014069432"},"language":"en","primary_location":{"id":"doi:10.1145/3373509.3373510","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3373509.3373510","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 8th International Conference on Computing and Pattern Recognition","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/A5025019732","display_name":"Dejian Zhong","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Dejian Zhong","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101810780","display_name":"Jie Lin","orcid":"https://orcid.org/0000-0002-1561-5839"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Lin","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5025019732"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19613449,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"400","last_page":"405"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9994000196456909,"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/T12676","display_name":"Machine Learning and ELM","score":0.9987999796867371,"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/initialization","display_name":"Initialization","score":0.7124657034873962},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.6570785045623779},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5746353268623352},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5436605215072632},{"id":"https://openalex.org/keywords/norm","display_name":"Norm (philosophy)","score":0.536938488483429},{"id":"https://openalex.org/keywords/rectifier","display_name":"Rectifier (neural networks)","score":0.5359704494476318},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5202523469924927},{"id":"https://openalex.org/keywords/connection","display_name":"Connection (principal bundle)","score":0.49086958169937134},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4817543029785156},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3733341693878174},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.36269187927246094},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.3594778776168823},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3590348958969116},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.30194222927093506},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.18989434838294983}],"concepts":[{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.7124657034873962},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6570785045623779},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5746353268623352},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5436605215072632},{"id":"https://openalex.org/C191795146","wikidata":"https://www.wikidata.org/wiki/Q3878446","display_name":"Norm (philosophy)","level":2,"score":0.536938488483429},{"id":"https://openalex.org/C50100734","wikidata":"https://www.wikidata.org/wiki/Q7303176","display_name":"Rectifier (neural networks)","level":5,"score":0.5359704494476318},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5202523469924927},{"id":"https://openalex.org/C13355873","wikidata":"https://www.wikidata.org/wiki/Q2920850","display_name":"Connection (principal bundle)","level":2,"score":0.49086958169937134},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4817543029785156},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3733341693878174},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.36269187927246094},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3594778776168823},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3590348958969116},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.30194222927093506},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.18989434838294983},{"id":"https://openalex.org/C86582703","wikidata":"https://www.wikidata.org/wiki/Q7617824","display_name":"Stochastic neural network","level":4,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3373509.3373510","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3373509.3373510","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 8th International Conference on Computing and Pattern Recognition","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1533861849","https://openalex.org/W1677182931","https://openalex.org/W1686810756","https://openalex.org/W1709548961","https://openalex.org/W1836465849","https://openalex.org/W2112796928","https://openalex.org/W2117539524","https://openalex.org/W2145287260","https://openalex.org/W2147800946","https://openalex.org/W2155893237","https://openalex.org/W2271840356","https://openalex.org/W2606722458","https://openalex.org/W2949117887","https://openalex.org/W2963942586","https://openalex.org/W3118608800","https://openalex.org/W3154811403","https://openalex.org/W4246999471"],"related_works":["https://openalex.org/W3204184292","https://openalex.org/W3176564347","https://openalex.org/W1985458517","https://openalex.org/W2355833770","https://openalex.org/W3031039437","https://openalex.org/W183202219","https://openalex.org/W3095877357","https://openalex.org/W2072565696","https://openalex.org/W2050451745","https://openalex.org/W2378903222"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,21,64],"investigate":[4],"regularization":[5,25],"method":[6,26,72,88],"to":[7,53,80,103],"construct":[8],"better":[9],"rectifier":[10,31,76],"neural":[11,32],"networks":[12,33],"for":[13,27,69],"the":[14,50,60,75,93,104],"classification":[15],"tasks":[16],"from":[17],"two":[18,46,56],"aspects.":[19],"First":[20],"propose":[22],"a":[23,43,66],"novel":[24],"effective":[28],"training":[29],"of":[30,45],"by":[34,73],"reparameterizing":[35],"each":[36],"connection":[37,61],"weight":[38,107],"in":[39],"convolution":[40],"layers":[41],"into":[42,78],"product":[44],"vectors":[47,57],"and":[48,95,98],"using":[49],"L2-norm":[51,106],"penalty":[52],"constrain":[54],"those":[55],"rather":[58],"than":[59],"weight.":[62],"Second,":[63],"derive":[65],"robust":[67],"initialization":[68],"our":[70],"reparameterization":[71],"taking":[74],"nonlinearities":[77],"account":[79],"help":[81],"learn":[82],"well":[83],"regularized":[84],"networks.":[85],"This":[86],"new":[87],"has":[89],"been":[90],"evaluated":[91],"on":[92],"CIFAR-10":[94],"CIFAR-100":[96],"datasets":[97],"demonstrated":[99],"improved":[100],"performance":[101],"relative":[102],"traditional":[105],"decay":[108],"approach.":[109]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}