{"id":"W3080221164","doi":"10.1038/s41467-020-18037-z","title":"Different scaling of linear models and deep learning in UKBiobank brain images versus machine-learning datasets","year":2020,"lang":"en","type":"article","venue":"Nature Communications","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":303,"is_retracted":false,"has_abstract":true,"ca_institutions":"Montreal Neurological Institute and Hospital; Mila - Quebec Artificial Intelligence Institute; McGill University; Canadian Institute for Advanced Research","funders":"National Institutes of Health; Canada First Research Excellence Fund; RWTH Aachen University; National Institute on Aging; National Research Foundation; Deutsche Forschungsgemeinschaft; National Research Foundation Singapore; Wellcome Trust; Canadian Institute for Advanced Research","keywords":"Scaling; Computer science; Deep learning; Artificial intelligence; Machine learning; Linear scale; Pattern recognition (psychology); Mathematics; Cartography; Geography","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0001984343,0.0001341037,0.0002033877,0.00009214009,0.0003974534,0.00002649896,0.0005518722,0.0001035183,0.000005574232],"category_scores_gemma":[0.0172216,0.0001301794,0.00003917448,0.0003730528,0.0001968875,0.0002039987,0.000966857,0.001579054,0.000003124293],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000298812,"about_ca_system_score_gemma":0.00001550168,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003132983,"about_ca_topic_score_gemma":0.0002358481,"domain_scores_codex":[0.9986619,0.0004710306,0.0002084891,0.0003139052,0.0001934404,0.0001512453],"domain_scores_gemma":[0.990431,0.008885828,0.000113146,0.0004711136,0.00004107618,0.00005789343],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00216273,0.001557235,0.0932343,0.000601435,0.0002988317,0.00003994635,0.02376914,0.1345644,0.5791036,0.1009469,0.007177324,0.05654419],"study_design_scores_gemma":[0.002237061,0.000261065,0.01044974,0.00009073751,0.00004125585,0.000006763527,0.0008667871,0.9415779,0.01490127,0.0006058731,0.02852682,0.0004347241],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6842008,0.03965901,0.004377615,0.2627746,0.0005146204,0.001310352,0.0008721997,0.000717704,0.005573056],"genre_scores_gemma":[0.9959585,0.001189791,0.001373592,0.001315937,0.00002271634,0.0000140557,0.00009798913,0.00001587968,0.00001151618],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8070135,"threshold_uncertainty_score":0.9910567,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07175583485518557,"score_gpt":0.3284353308647029,"score_spread":0.2566794960095174,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}