{"id":"https://openalex.org/W4225316133","doi":"https://doi.org/10.1109/southeastcon48659.2022.9763950","title":"Gradient Difference-Predictive Coding Network (GD-PredNet): Reducing the Convergence Time for Future Frame Prediction with Infinitesimal Quality Trade-off","display_name":"Gradient Difference-Predictive Coding Network (GD-PredNet): Reducing the Convergence Time for Future Frame Prediction with Infinitesimal Quality Trade-off","publication_year":2022,"publication_date":"2022-03-26","ids":{"openalex":"https://openalex.org/W4225316133","doi":"https://doi.org/10.1109/southeastcon48659.2022.9763950"},"language":"en","primary_location":{"id":"doi:10.1109/southeastcon48659.2022.9763950","doi":"https://doi.org/10.1109/southeastcon48659.2022.9763950","is_oa":false,"landing_page_url":"https://doi.org/10.1109/southeastcon48659.2022.9763950","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":"SoutheastCon 2022","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","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/A5087029037","display_name":"Sai Ranganath Mikkilineni","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I79516672","display_name":"University of Louisiana at Lafayette","ror":"https://ror.org/01x8rc503","country_code":"US","type":"education","lineage":["https://openalex.org/I2799628689","https://openalex.org/I79516672"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sai Ranganath Mikkilineni","raw_affiliation_strings":["University of Louisiana at Lafayette,Center for Advanced Computer Studies,Lafayette,LA,USA","Center for Advanced Computer Studies, University of Louisiana at Lafayette, Lafayette, LA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Louisiana at Lafayette,Center for Advanced Computer Studies,Lafayette,LA,USA","institution_ids":["https://openalex.org/I79516672"]},{"raw_affiliation_string":"Center for Advanced Computer Studies, University of Louisiana at Lafayette, Lafayette, LA, USA","institution_ids":["https://openalex.org/I79516672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091804773","display_name":"Taylor D. Privat","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I79516672","display_name":"University of Louisiana at Lafayette","ror":"https://ror.org/01x8rc503","country_code":"US","type":"education","lineage":["https://openalex.org/I2799628689","https://openalex.org/I79516672"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Taylor D. Privat","raw_affiliation_strings":["University of Louisiana at Lafayette,Center for Advanced Computer Studies,Lafayette,LA,USA","Center for Advanced Computer Studies, University of Louisiana at Lafayette, Lafayette, LA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Louisiana at Lafayette,Center for Advanced Computer Studies,Lafayette,LA,USA","institution_ids":["https://openalex.org/I79516672"]},{"raw_affiliation_string":"Center for Advanced Computer Studies, University of Louisiana at Lafayette, Lafayette, LA, USA","institution_ids":["https://openalex.org/I79516672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060930128","display_name":"Michael Wayne Totaro","orcid":"https://orcid.org/0000-0002-8311-1042","observed_orcids":["https://orcid.org/0000-0002-8311-1042"]},"institutions":[{"id":"https://openalex.org/I79516672","display_name":"University of Louisiana at Lafayette","ror":"https://ror.org/01x8rc503","country_code":"US","type":"education","lineage":["https://openalex.org/I2799628689","https://openalex.org/I79516672"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Wayne Totaro","raw_affiliation_strings":["University of Louisiana at Lafayette,Center for Advanced Computer Studies,Lafayette,LA,USA","Center for Advanced Computer Studies, University of Louisiana at Lafayette, Lafayette, LA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Louisiana at Lafayette,Center for Advanced Computer Studies,Lafayette,LA,USA","institution_ids":["https://openalex.org/I79516672"]},{"raw_affiliation_string":"Center for Advanced Computer Studies, University of Louisiana at Lafayette, Lafayette, LA, USA","institution_ids":["https://openalex.org/I79516672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I79516672"],"apc_list":null,"apc_paid":null,"fwci":0.1615,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.42223581,"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":"281","last_page":"288"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.30959999561309814,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.30959999561309814,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.125,"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":0.06930000334978104,"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/prednet","display_name":"PredNet","score":0.6830000281333923},{"id":"https://openalex.org/keywords/predictive-coding","display_name":"predictive coding","score":0.7170000076293945},{"id":"https://openalex.org/keywords/future-frame-prediction","display_name":"future frame prediction","score":0.9570000171661377},{"id":"https://openalex.org/keywords/video-prediction","display_name":"video prediction","score":0.7160000205039978},{"id":"https://openalex.org/keywords/convergence-rate","display_name":"convergence rate","score":0.7049999833106995},{"id":"https://openalex.org/keywords/quality-trade-offs","display_name":"quality trade-offs","score":0.7720000147819519},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"unsupervised learning","score":0.7710000276565552},{"id":"https://openalex.org/keywords/free-energy-principle","display_name":"free energy principle","score":0.671999990940094}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7148067355155945},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5321542024612427},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5028595328330994},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4912678599357605},{"id":"https://openalex.org/C39394851","wikidata":"https://www.wikidata.org/wiki/Q921594","display_name":"Inter frame","level":4,"score":0.4519384801387787},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.43918517231941223},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4389514923095703},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.43093299865722656},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.4131772220134735},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4108758568763733},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24026402831077576},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.220506489276886},{"id":"https://openalex.org/C172849965","wikidata":"https://www.wikidata.org/wiki/Q3148875","display_name":"Reference frame","level":3,"score":0.13356974720954895},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10557514429092407},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/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/southeastcon48659.2022.9763950","doi":"https://doi.org/10.1109/southeastcon48659.2022.9763950","is_oa":false,"landing_page_url":"https://doi.org/10.1109/southeastcon48659.2022.9763950","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":"SoutheastCon 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W1542873368","https://openalex.org/W1545934923","https://openalex.org/W1594551768","https://openalex.org/W2074466695","https://openalex.org/W2101032778","https://openalex.org/W2107775979","https://openalex.org/W2115579991","https://openalex.org/W2117731089","https://openalex.org/W2119885245","https://openalex.org/W2248556341","https://openalex.org/W2401640538","https://openalex.org/W2625366777","https://openalex.org/W2883615717","https://openalex.org/W2963610939","https://openalex.org/W2996680032","https://openalex.org/W3015256491","https://openalex.org/W3024322256","https://openalex.org/W3215054920","https://openalex.org/W6600983433"],"related_works":["https://openalex.org/W4292122428","https://openalex.org/W3022649450","https://openalex.org/W4316829940","https://openalex.org/W2248556341","https://openalex.org/W2808011586","https://openalex.org/W4417282177","https://openalex.org/W4225261492","https://openalex.org/W2969399927","https://openalex.org/W3134795618","https://openalex.org/W4308331462"],"abstract_inverted_index":{"Even":[0],"though":[1],"future":[2,37,141],"frame":[3,38,142],"prediction":[4],"in":[5,28,140,255],"videos":[6],"is":[7,63,85,217],"a":[8,29,41,46,65,97,147,206,234],"relatively":[9,66],"young":[10,67],"unsupervised":[11],"learning":[12,42,122],"task,":[13],"it":[14,62,117,185],"has":[15,45],"shown":[16],"promise":[17,120],"by":[18,96,167],"accommodating":[19],"the":[20,59,89,92,105,110,114,152,160,176,180,192,209,222,231],"networks":[21],"to":[22,70,136,174,179,219,221,251],"effectively":[23],"learn":[24],"efficient":[25],"internal":[26,94,125],"representations":[27,95,126],"visual":[30,60],"hyperspace.":[31],"Predictive":[32,81,256],"Coding":[33,82,257],"Network":[34],"(PredNet)":[35],"uses":[36,186],"predictions":[39,232],"as":[40,151],"signal":[43],"and":[44,54,73,78,99,248,258],"legacy":[47],"background":[48],"of":[49,58,104,113,182,208,230],"unconscious":[50],"inference,":[51],"free":[52],"energy,":[53],"predictive":[55],"coding":[56],"model":[57,84],"cortex;":[61],"still":[64,118],"network":[68],"compared":[69],"RNNs,":[71],"CNNs,":[72],"so":[74],"on.":[75],"Although":[76],"Rao":[77],"Ballard\u2019s":[79],"proposed":[80,166],"(PC)":[83],"aimed":[86],"at":[87],"reducing":[88],"redundancy":[90],"within":[91,233],"learned":[93],"network,":[98],"Lotter":[100],"et":[101,169],"al.\u2019s":[102],"design":[103],"PredNet":[106,135,183,243],"might":[107],"not":[108],"be":[109],"ideal":[111],"replication":[112],"PC":[115],"model,":[116],"shows":[119],"for":[121],"better":[123],"less-redundant":[124],"than":[127],"other":[128],"networks.":[129],"In":[130,238],"this":[131,173],"paper,":[132],"we":[133,145,241,249],"augment":[134],"enhance":[137],"its":[138],"performance":[139,224],"prediction.":[143],"Additionally,":[144],"introduce":[146],"new":[148],"measure":[149,157],"known":[150],"gradient":[153,161],"difference":[154,162],"error":[155],"(GDE)":[156],"based":[158],"on":[159],"loss":[163,189,194,211],"(GDL)":[164],"function":[165,178,190,212],"Mathieu":[168],"al.":[170],"We":[171],"do":[172],"adapt":[175],"GDL":[177],"context":[181],"since":[184],"an":[187],"implicit":[188],"besides":[191],"explicit":[193],"used":[195],"during":[196],"training.":[197],"Our":[198],"experimental":[199],"results":[200],"show":[201],"that":[202],"PredNet,":[203],"when":[204],"using":[205],"combination":[207],"L1":[210],"with":[213],"GDE":[214],"or":[215],"GDL,":[216],"faster":[218],"converge":[220],"best":[223],"while":[225],"trading":[226],"off":[227],"minimal":[228],"quality":[229],"given":[235],"training":[236],"window.":[237],"doing":[239],"so,":[240],"transform":[242],"into":[244],"Gradient":[245],"Difference-PredNet":[246],"(GD-PredNet),":[247],"aim":[250],"encourage":[252],"increased":[253],"research":[254],"PredNet.":[259]},"counts_by_year":[{"year":2023,"cited_by_count":2}],"updated_date":"2026-10-26T11:51:55.731654","created_date":"2022-05-05T00:00:00"}