{"id":"https://openalex.org/W7154703074","doi":"https://doi.org/10.48550/arxiv.2604.14645","title":"Chaotic CNN for Limited Data Image Classification","display_name":"Chaotic CNN for Limited Data Image Classification","publication_year":2026,"publication_date":"2026-04-16","ids":{"openalex":"https://openalex.org/W7154703074","doi":"https://doi.org/10.48550/arxiv.2604.14645"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.14645","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.14645","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.2604.14645","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133870199","display_name":"Anusree M","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"M, Anusree","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130827803","display_name":"Akhila Henry","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Henry, Akhila","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5051479917","display_name":"Pramod P Nair","orcid":"https://orcid.org/0000-0001-6142-5326"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nair, Pramod P","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5133870199"],"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.3483999967575073,"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"}},"topics":[{"id":"https://openalex.org/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.3483999967575073,"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":0.0771000012755394,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.05469999834895134,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.7712000012397766},{"id":"https://openalex.org/keywords/mnist-database","display_name":"MNIST database","score":0.7670999765396118},{"id":"https://openalex.org/keywords/skew","display_name":"Skew","score":0.6808000206947327},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6626999974250793},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6126999855041504},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6050999760627747},{"id":"https://openalex.org/keywords/chaotic","display_name":"Chaotic","score":0.546500027179718},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.4336000084877014}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7712000012397766},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.7670999765396118},{"id":"https://openalex.org/C43711488","wikidata":"https://www.wikidata.org/wiki/Q7534783","display_name":"Skew","level":2,"score":0.6808000206947327},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6626999974250793},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.657800018787384},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6126999855041504},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6050999760627747},{"id":"https://openalex.org/C2777052490","wikidata":"https://www.wikidata.org/wiki/Q5072826","display_name":"Chaotic","level":2,"score":0.546500027179718},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5157999992370605},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.4336000084877014},{"id":"https://openalex.org/C78201319","wikidata":"https://www.wikidata.org/wiki/Q685727","display_name":"Grayscale","level":3,"score":0.4250999987125397},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.40369999408721924},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.37860000133514404},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3702000081539154},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3571000099182129},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.34769999980926514},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.31859999895095825},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.28130000829696655},{"id":"https://openalex.org/C812465","wikidata":"https://www.wikidata.org/wiki/Q5058375","display_name":"Cellular neural network","level":3,"score":0.27959999442100525},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27239999175071716},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2587999999523163}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.14645","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.14645","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.2604.14645","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.14645","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":[{"display_name":"No poverty","id":"https://metadata.un.org/sdg/1","score":0.5087646245956421}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Convolutional":[0],"neural":[1],"networks":[2],"(CNNs)":[3],"often":[4],"exhibit":[5],"poor":[6],"generalisation":[7],"in":[8],"limited":[9,91],"training":[10],"data":[11,92],"scenarios":[12],"due":[13],"to":[14,32,52],"overfitting":[15],"and":[16,25,49,65,77,79,192,209],"insufficient":[17],"feature":[18,28,54,63],"diversity.":[19],"In":[20],"this":[21],"work,":[22],"a":[23,108,124,146,155,220],"simple":[24],"effective":[26],"chaos-based":[27],"transformation":[29],"is":[30,71,114,137,160,186,201],"proposed":[31,199],"enhance":[33],"CNN":[34,85,103,126,148,216],"performance":[35,110,184],"without":[36],"increasing":[37],"model":[38],"complexity.":[39],"The":[40,69,94,174,198],"method":[41,200],"applies":[42],"nonlinear":[43,191],"transformations":[44],"using":[45,84,118,141,164],"logistic,":[46],"skew":[47,120,166],"tent,":[48],"sine":[50,143],"maps":[51,180],"normalised":[53],"vectors":[55],"before":[56],"the":[57,62,100,119,142,165,183,189],"classification":[58,226],"layer,":[59],"thereby":[60],"reshaping":[61],"space":[64],"improving":[66],"class":[67],"separability.":[68],"approach":[70],"evaluated":[72],"on":[73,116,139,162],"greyscale":[74],"datasets":[75],"(MNIST":[76],"Fashion-MNIST)":[78],"an":[80],"RGB":[81],"dataset":[82],"(CIFAR-10)":[83],"architectures":[86],"of":[87,112,135,158,195],"varying":[88],"depth":[89],"under":[90],"conditions.":[93],"results":[95],"show":[96],"consistent":[97,175],"improvement":[98],"over":[99],"standalone":[101],"(SA)":[102],"across":[104,177],"all":[105],"datasets.":[106],"Notably,":[107],"maximum":[109],"gain":[111,134,157,185],"5.43%":[113],"achieved":[115],"MNIST":[117],"tent":[121,167],"map":[122,144,168],"with":[123,145],"3-layer":[125,147],"at":[127,149,169],"40":[128],"samples":[129,151,171],"per":[130,152,172],"class.":[131,153,173],"A":[132],"higher":[133],"9.11%":[136],"observed":[138],"Fashion-MNIST":[140],"50":[150],"Additionally,":[154],"strong":[156],"7.47%":[159],"obtained":[161],"CIFAR-10":[163],"200":[170],"improvements":[176],"different":[178],"chaotic":[179,196],"indicate":[181],"that":[182],"driven":[187],"by":[188],"shared":[190],"dynamical":[193],"properties":[194],"systems.":[197],"computationally":[202],"efficient,":[203],"requires":[204],"no":[205],"additional":[206],"trainable":[207],"parameters,":[208],"can":[210],"be":[211],"easily":[212],"integrated":[213],"into":[214],"existing":[215],"architectures,":[217],"making":[218],"it":[219],"practical":[221],"solution":[222],"for":[223],"data-scarce":[224],"image":[225],"tasks.":[227]},"counts_by_year":[],"updated_date":"2026-04-18T06:05:20.339008","created_date":"2026-04-18T00:00:00"}