{"id":"https://openalex.org/W2552955516","doi":"https://doi.org/10.1109/ijcnn.2016.7727307","title":"Training deep neural networks with gradual deconvexification","display_name":"Training deep neural networks with gradual deconvexification","publication_year":2016,"publication_date":"2016-07-01","ids":{"openalex":"https://openalex.org/W2552955516","doi":"https://doi.org/10.1109/ijcnn.2016.7727307","mag":"2552955516"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2016.7727307","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2016.7727307","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 International Joint Conference on Neural Networks (IJCNN)","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/A5104056506","display_name":"James Lo","orcid":null},"institutions":[{"id":"https://openalex.org/I126744593","display_name":"University of Maryland, Baltimore","ror":"https://ror.org/04rq5mt64","country_code":"US","type":"education","lineage":["https://openalex.org/I126744593"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"James Ting-Ho Lo","raw_affiliation_strings":["Department of Mathematics and Statistics, University of Maryland, Baltimore"],"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Statistics, University of Maryland, Baltimore","institution_ids":["https://openalex.org/I126744593"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020343615","display_name":"Yichuan Gui","orcid":null},"institutions":[{"id":"https://openalex.org/I126744593","display_name":"University of Maryland, Baltimore","ror":"https://ror.org/04rq5mt64","country_code":"US","type":"education","lineage":["https://openalex.org/I126744593"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yichuan Gui","raw_affiliation_strings":["Department of Mathematics and Statistics, University of Maryland, Baltimore"],"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Statistics, University of Maryland, Baltimore","institution_ids":["https://openalex.org/I126744593"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065293431","display_name":"Yun Peng","orcid":"https://orcid.org/0000-0002-6891-180X"},"institutions":[{"id":"https://openalex.org/I126744593","display_name":"University of Maryland, Baltimore","ror":"https://ror.org/04rq5mt64","country_code":"US","type":"education","lineage":["https://openalex.org/I126744593"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yun Peng","raw_affiliation_strings":["Department of Mathematics and Statistics, University of Maryland, Baltimore"],"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Statistics, University of Maryland, Baltimore","institution_ids":["https://openalex.org/I126744593"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5104056506"],"corresponding_institution_ids":["https://openalex.org/I126744593"],"apc_list":null,"apc_paid":null,"fwci":0.167,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.58474164,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1000","last_page":"1007"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10688","display_name":"Image and Signal Denoising Methods","score":0.9990000128746033,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9990000128746033,"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/T10320","display_name":"Neural Networks and Applications","score":0.9976999759674072,"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/maxima-and-minima","display_name":"Maxima and minima","score":0.8376438617706299},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6908440589904785},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.6756176948547363},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6607153415679932},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.6595563292503357},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6019025444984436},{"id":"https://openalex.org/keywords/saddle-point","display_name":"Saddle point","score":0.569432258605957},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5386614203453064},{"id":"https://openalex.org/keywords/saddle","display_name":"Saddle","score":0.5344974398612976},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5301262736320496},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5181023478507996},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.49185800552368164},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4763619899749756},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4676026403903961},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3562559485435486},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.2523205280303955},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21348941326141357},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.06575477123260498}],"concepts":[{"id":"https://openalex.org/C186633575","wikidata":"https://www.wikidata.org/wiki/Q845060","display_name":"Maxima and minima","level":2,"score":0.8376438617706299},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6908440589904785},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.6756176948547363},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6607153415679932},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.6595563292503357},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6019025444984436},{"id":"https://openalex.org/C2681867","wikidata":"https://www.wikidata.org/wiki/Q690935","display_name":"Saddle point","level":2,"score":0.569432258605957},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5386614203453064},{"id":"https://openalex.org/C2777127463","wikidata":"https://www.wikidata.org/wiki/Q10862618","display_name":"Saddle","level":2,"score":0.5344974398612976},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5301262736320496},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5181023478507996},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.49185800552368164},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4763619899749756},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4676026403903961},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3562559485435486},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2523205280303955},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21348941326141357},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.06575477123260498},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn.2016.7727307","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2016.7727307","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 International Joint Conference on Neural Networks (IJCNN)","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":32,"referenced_works":["https://openalex.org/W32532385","https://openalex.org/W44815768","https://openalex.org/W189596042","https://openalex.org/W1513807349","https://openalex.org/W1899249567","https://openalex.org/W1936332779","https://openalex.org/W1982969160","https://openalex.org/W1996269175","https://openalex.org/W2110798204","https://openalex.org/W2112796928","https://openalex.org/W2136922672","https://openalex.org/W2138857742","https://openalex.org/W2160815625","https://openalex.org/W2163605009","https://openalex.org/W2546191734","https://openalex.org/W2606321545","https://openalex.org/W2613634265","https://openalex.org/W2963586744","https://openalex.org/W2998704965","https://openalex.org/W4231109964","https://openalex.org/W4238404964","https://openalex.org/W4251996061","https://openalex.org/W4253157822","https://openalex.org/W4285719527","https://openalex.org/W6601344651","https://openalex.org/W6607775107","https://openalex.org/W6639736602","https://openalex.org/W6676481782","https://openalex.org/W6680300913","https://openalex.org/W6680532216","https://openalex.org/W6681804681","https://openalex.org/W6684191040"],"related_works":["https://openalex.org/W4210838092","https://openalex.org/W2121922170","https://openalex.org/W1557737441","https://openalex.org/W131971937","https://openalex.org/W2095858157","https://openalex.org/W1996762907","https://openalex.org/W2752635268","https://openalex.org/W2324860879","https://openalex.org/W2021599769","https://openalex.org/W3114201969"],"abstract_inverted_index":{"A":[0],"new":[1],"method":[2,15,36,74],"of":[3,59,82,93],"training":[4],"deep":[5],"neural":[6,84],"networks":[7],"including":[8],"the":[9,17,26,40,47,57,68,79,83,94],"convolutional":[10],"network":[11,85],"is":[12,32,75],"proposed.":[13],"The":[14,35],"deconvexifies":[16],"normalized":[18],"risk-averting":[19,27],"error":[20,28],"(NRAE)":[21],"gradually":[22],"and":[23,49],"switches":[24],"to":[25,77],"(RAE)":[29],"whenever":[30],"RAE":[31],"computationally":[33],"manageable.":[34],"creates":[37],"tunnels":[38],"between":[39],"depressed":[41],"regions":[42],"around":[43],"saddle":[44],"points,":[45],"tilts":[46],"plateaus,":[48],"eliminates":[50],"nonglobal":[51],"local":[52],"minima.":[53],"Numerical":[54,88],"experiments":[55],"show":[56,90],"effectiveness":[58],"gradual":[60],"deconvexification":[61],"as":[62],"compared":[63],"with":[64],"unsupervised":[65],"pretraining.":[66],"After":[67],"minimization":[69],"process,":[70],"a":[71],"statistical":[72],"pruning":[73],"used":[76],"enhance":[78],"generalization":[80],"capability":[81],"under":[86],"training.":[87],"results":[89],"further":[91],"reduction":[92],"testing":[95],"criterion.":[96]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}