{"id":"W2971608886","doi":"10.1101/757054","title":"Deep learning for brains?: Different linear and nonlinear scaling in UK Biobank brain images vs. machine-learning datasets","year":2019,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; McGill University; Canadian Institute for Advanced Research","funders":"RWTH Aachen University; Deutsche Forschungsgemeinschaft","keywords":"Deep learning; Biobank; Artificial intelligence; Linear model; Computer science; Nonlinear system; Machine learning; Kernel (algebra); MNIST database; Neuroimaging; Sample (material); Linear scale; Contrast (vision); Pattern recognition (psychology); Mathematics; Psychology; Geography; Neuroscience; Cartography","routes":{"ca_aff":true,"ca_fund":false,"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":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.002382058,0.001129915,0.001334782,0.0009030378,0.0005069125,0.0008499414,0.002095593,0.000845852,0.0000162108],"category_scores_gemma":[0.002934255,0.001193122,0.000233822,0.0007448226,0.0001421239,0.0004148318,0.003141271,0.003986761,0.00003585905],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000367741,"about_ca_system_score_gemma":0.0004247228,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004366087,"about_ca_topic_score_gemma":0.00003620488,"domain_scores_codex":[0.9930451,0.0009800706,0.001196169,0.002689095,0.0007056178,0.00138398],"domain_scores_gemma":[0.9949428,0.001231235,0.0009479698,0.00206523,0.0003092005,0.0005035379],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002933328,0.0005085904,0.8575293,0.00845646,0.0003889062,0.0003352742,0.0005053389,0.07829483,0.05055506,0.00191905,0.0005120863,0.0007017821],"study_design_scores_gemma":[0.001347805,0.0002352421,0.1160486,0.001028526,0.00004070159,2.045112e-7,0.000005442628,0.8676839,0.004587507,0.000007907342,0.007605745,0.001408358],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6598451,0.005702498,0.3213195,0.00501865,0.002451486,0.003461464,0.0005773988,0.001617128,0.000006882663],"genre_scores_gemma":[0.9159926,0.0004490301,0.08186474,0.0006553612,0.0005375532,0.0002280184,0.00002585405,0.0002335121,0.00001330478],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7893891,"threshold_uncertainty_score":0.9990519,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01395249017492114,"score_gpt":0.2600396866145979,"score_spread":0.2460871964396768,"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."}}