{"id":"https://openalex.org/W7156941771","doi":"https://doi.org/10.48550/arxiv.2604.24637","title":"Cortex-Inspired Continual Learning: Unsupervised Instantiation and Recovery of Functional Task Networks","display_name":"Cortex-Inspired Continual Learning: Unsupervised Instantiation and Recovery of Functional Task Networks","publication_year":2026,"publication_date":"2026-04-27","ids":{"openalex":"https://openalex.org/W7156941771","doi":"https://doi.org/10.48550/arxiv.2604.24637"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.24637","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.24637","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":null,"license_id":null,"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.2604.24637","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035444135","display_name":"Kevin McKee","orcid":"https://orcid.org/0000-0002-8795-7555"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"McKee, Kevin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134754240","display_name":"Thomas Hazy","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hazy, Thomas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002080971","display_name":"Yicong Zheng","orcid":"https://orcid.org/0000-0003-4925-6069"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Yicong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130098994","display_name":"Zacharie Bugaud","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bugaud, Zacharie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5076867146","display_name":"Thomas Miconi","orcid":"https://orcid.org/0000-0002-7897-4492"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Miconi, Thomas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9800999760627747,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9800999760627747,"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":0.0013000000035390258,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0013000000035390258,"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/mnist-database","display_name":"MNIST database","score":0.8889999985694885},{"id":"https://openalex.org/keywords/disjoint-sets","display_name":"Disjoint sets","score":0.6822999715805054},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.6110000014305115},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5910999774932861},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.49880000948905945},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.46860000491142273},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.45680001378059387},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4440000057220459},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4262000024318695}],"concepts":[{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.8889999985694885},{"id":"https://openalex.org/C45340560","wikidata":"https://www.wikidata.org/wiki/Q215382","display_name":"Disjoint sets","level":2,"score":0.6822999715805054},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6262999773025513},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.6110000014305115},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6108999848365784},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5910999774932861},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.49880000948905945},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.46860000491142273},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.45680001378059387},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4440000057220459},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4262000024318695},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.36980000138282776},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3646000027656555},{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.35749998688697815},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.3357999920845032},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.3305000066757202},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3280999958515167},{"id":"https://openalex.org/C39891107","wikidata":"https://www.wikidata.org/wiki/Q5767098","display_name":"Hinge loss","level":3,"score":0.3140999972820282},{"id":"https://openalex.org/C2777984123","wikidata":"https://www.wikidata.org/wiki/Q9248237","display_name":"Pointwise","level":2,"score":0.3131999969482422},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.30720001459121704},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.28619998693466187},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.28360000252723694},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.2833000123500824},{"id":"https://openalex.org/C114275822","wikidata":"https://www.wikidata.org/wiki/Q621512","display_name":"Linear dynamical system","level":3,"score":0.26919999718666077},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.257099986076355},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.25540000200271606},{"id":"https://openalex.org/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"score":0.2540000081062317}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.24637","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.24637","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.24637","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.24637","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":null,"license_id":null,"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":{"Block-sequential":[0],"continual":[1],"learning":[2],"demands":[3],"that":[4,227],"a":[5,37,57,64,84,91,98,115,149,153,172,208,249],"single":[6,154],"model":[7],"both":[8],"protect":[9],"prior":[10,22],"solutions":[11],"from":[12,237],"catastrophic":[13,140],"forgetting":[14],"and":[15,43,108,186,211],"efficiently":[16],"infer":[17],"at":[18,114,161],"inference":[19,162],"time":[20],"which":[21,258],"solution":[23],"matches":[24],"the":[25,48,102,111,146,228,233,238,246,262],"current":[26],"input":[27],"without":[28],"task":[29,151,159],"labels.":[30],"We":[31,164,225],"present":[32],"Functional":[33],"Task":[34],"Networks":[35],"(FTN),":[36],"parameter-isolation":[38],"method":[39,55],"inspired":[40,72],"by":[41,73,83,261],"structural":[42,137],"dynamical":[44],"motifs":[45],"found":[46],"in":[47,152,202,243,252],"mammalian":[49],"neocortex.":[50],"Similar":[51],"to":[52,245],"mixture-of-experts,":[53,120],"this":[54],"uses":[56],"high":[58],"dimensional,":[59],"self-organizing":[60],"binary":[61],"mask":[62,80,93,235],"over":[63,254],"large":[65,209],"population":[66],"of":[67,76,148,215,248],"small":[68],"but":[69],"deep":[70,126],"networks,":[71],"dendritic":[74],"models":[75],"pyramidal":[77],"neurons.":[78],"The":[79],"is":[81,123,259],"produced":[82],"three-stage":[85,143],"procedure:":[86],"(1)":[87,171],"gradient":[88,134,155],"descent":[89],"on":[90,167],"continuous":[92],"identifies":[94],"task-relevant":[95],"neurons,":[96],"(2)":[97,177],"smoothing":[99,199,216],"kernel":[100,210],"biases":[101],"result":[103],"toward":[104],"spatial":[105,229],"contiguity,":[106],"(3)":[107,187],"k-winner-take-all":[109],"binarizes":[110],"resulting":[112],"group":[113],"fixed":[116],"capacity":[117],"budget.":[118],"Like":[119],"each":[121],"neuron":[122],"an":[124],"independent":[125],"network,":[127],"so":[128],"disjoint":[129,133],"masks":[130],"give":[131],"exactly":[132],"updates,":[135],"providing":[136,157],"guarantees":[138],"against":[139],"forgetting.":[141,205],"This":[142],"procedure":[144],"recovers":[145],"sub-network":[147],"previously-trained":[150],"step,":[156],"unsupervised":[158],"segmentation":[160],"time.":[163],"test":[165],"it":[166],"three":[168],"continual-learning":[169],"benchmarks:":[170],"synthetic":[173],"multi-task":[174],"classification/regression":[175],"generator,":[176],"MNIST":[178,189],"with":[179,196,207],"shuffled":[180],"class":[181],"labels":[182],"(pure":[183],"concept":[184],"shift),":[185],"Permuted":[188],"(domain":[190],"shift).":[191],"On":[192],"all":[193],"three,":[194],"FTN":[195,206],"fine":[197],"grained":[198],"(FTN-Slow)":[200],"results":[201],"nearly":[203],"zero":[204],"only":[212],"2":[213],"iterations":[214],"(FTN-Fast)":[217],"trades":[218],"off":[219],"some":[220],"retention":[221],"for":[222],"increased":[223],"speed.":[224],"show":[226],"organization":[230],"mechanism":[231],"reduces":[232],"effective":[234],"search":[236],"combinatorial":[239],"top-k":[240],"subset":[241],"problem":[242],"O(C(H,K))":[244],"complexity":[247],"near-linear":[250],"scan":[251],"O(H)":[253],"compact":[255],"cortical":[256],"neighborhoods,":[257],"parallelized":[260],"gradient-based":[263],"update.":[264]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-04-29T00:00:00"}