{"id":"https://openalex.org/W7154373010","doi":"https://doi.org/10.48550/arxiv.2604.09716","title":"Training Deep Visual Networks Beyond Loss and Accuracy Through a Dynamical Systems Approach","display_name":"Training Deep Visual Networks Beyond Loss and Accuracy Through a Dynamical Systems Approach","publication_year":2026,"publication_date":"2026-04-08","ids":{"openalex":"https://openalex.org/W7154373010","doi":"https://doi.org/10.48550/arxiv.2604.09716"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.09716","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.09716","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.09716","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133559588","display_name":"Hai La Quang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"La Quang, Hai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083781406","display_name":"Hassan Ugail","orcid":"https://orcid.org/0000-0002-3084-1797"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ugail, Hassan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042535938","display_name":"Newton Howard","orcid":"https://orcid.org/0000-0002-8503-3973"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Howard, Newton","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133589394","display_name":"Cong Tran Tien","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tien, Cong Tran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133613610","display_name":"Nam Vu Hoai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hoai, Nam Vu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133572755","display_name":"Hung Nguyen Viet","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Viet, Hung Nguyen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T11094","display_name":"Face Recognition and Perception","score":0.617900013923645,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11094","display_name":"Face Recognition and Perception","score":0.617900013923645,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.03700000047683716,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.03009999915957451,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4487999975681305},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.41029998660087585},{"id":"https://openalex.org/keywords/dynamical-systems-theory","display_name":"Dynamical systems theory","score":0.4052000045776367},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4050000011920929},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.3968999981880188},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.3441999852657318},{"id":"https://openalex.org/keywords/backpropagation","display_name":"Backpropagation","score":0.3009999990463257},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.2992999851703644}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6585999727249146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6473000049591064},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4717999994754791},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4487999975681305},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.41029998660087585},{"id":"https://openalex.org/C79379906","wikidata":"https://www.wikidata.org/wiki/Q3174497","display_name":"Dynamical systems theory","level":2,"score":0.4052000045776367},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4050000011920929},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3968999981880188},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.3441999852657318},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.3009999990463257},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.2992999851703644},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.2955999970436096},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.2946999967098236},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C43091099","wikidata":"https://www.wikidata.org/wiki/Q1067788","display_name":"Through-the-lens metering","level":3,"score":0.28619998693466187},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.28200000524520874},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.2754000127315521},{"id":"https://openalex.org/C168820333","wikidata":"https://www.wikidata.org/wiki/Q448889","display_name":"Visual inspection","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.2624000012874603},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2574000060558319}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.09716","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.09716","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.09716","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.09716","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Deep":[0],"visual":[1,209],"recognition":[2],"models":[3],"are":[4],"usually":[5],"trained":[6],"and":[7,14,101,105,121,130,137,186,213],"evaluated":[8],"using":[9],"metrics":[10],"such":[11],"as":[12],"loss":[13,212],"accuracy.":[15,214],"While":[16],"these":[17],"measures":[18,72],"show":[19],"whether":[20],"a":[21,40,89,106,131],"model":[22,119],"is":[23],"improving,":[24],"they":[25],"reveal":[26],"very":[27],"little":[28],"about":[29],"how":[30,94],"its":[31],"internal":[32],"representations":[33],"change":[34],"during":[35],"training.":[36],"This":[37],"paper":[38],"introduces":[39],"complementary":[41],"way":[42,205],"to":[43,64,115,189,206],"study":[44,65,198],"that":[45,83,92],"process":[46],"by":[47],"examining":[48],"training":[49,78,194,210],"through":[50],"the":[51,96,146,151,156,164,167,182],"lens":[52],"of":[53,118,166,175,193],"dynamical":[54,108],"systems.":[55],"Drawing":[56],"on":[57,135],"ideas":[58],"from":[59,73,155],"signal":[60],"analysis":[61],"originally":[62],"used":[63],"biological":[66],"neural":[67],"activity,":[68],"we":[69],"define":[70],"three":[71,142],"layer":[74],"activations":[75],"collected":[76],"across":[77,87],"epochs:":[79],"an":[80,172,200],"integration":[81,147,185],"score":[82,91],"reflects":[84],"long-range":[85],"coordination":[86],"layers,":[88],"metastability":[90,187],"captures":[93],"flexibly":[95],"network":[97],"shifts":[98],"between":[99,184],"more":[100,157],"less":[102],"synchronised":[103],"states,":[104],"combined":[107],"stability":[109,168],"index.":[110],"We":[111],"apply":[112],"this":[113,197],"framework":[114],"nine":[116],"combinations":[117],"architecture":[120],"dataset,":[122],"including":[123],"several":[124],"ResNet":[125],"variants,":[126],"DenseNet-121,":[127],"MobileNetV2,":[128],"VGG-16,":[129],"pretrained":[132],"Vision":[133],"Transformer":[134],"CIFAR-10":[136,153],"CIFAR-100.":[138],"The":[139],"results":[140],"suggest":[141],"main":[143],"patterns.":[144],"First,":[145],"measure":[148],"consistently":[149],"distinguishes":[150],"easier":[152],"setting":[154],"difficult":[158],"CIFAR-100":[159],"setting.":[160],"Second,":[161],"changes":[162],"in":[163],"volatility":[165],"index":[169],"may":[170],"provide":[171],"early":[173],"sign":[174],"convergence":[176],"before":[177],"accuracy":[178],"fully":[179],"plateaus.":[180],"Third,":[181],"relationship":[183],"appears":[188],"reflect":[190],"different":[191],"styles":[192],"behaviour.":[195],"Overall,":[196],"offers":[199],"exploratory":[201],"but":[202],"promising":[203],"new":[204],"understand":[207],"deep":[208],"beyond":[211]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-04-15T00:00:00"}