{"id":"W3085768000","doi":"10.1088/1741-2552/abb7a7","title":"Thinker invariance: enabling deep neural networks for BCI across more people","year":2020,"lang":"en","type":"article","venue":"Journal of Neural Engineering","topic":"EEG and Brain-Computer Interfaces","field":"Neuroscience","cited_by":91,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; St. Michael's Hospital; Vector Institute","funders":"Natural Sciences and Engineering Research Council of Canada; Electronics and Telecommunications Research Institute","keywords":"Generality; Computer science; Brain–computer interface; Artificial intelligence; Machine learning; Classifier (UML); Transfer of learning; Deep neural networks; Invariant (physics); Artificial neural network; Electroencephalography","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001302956,0.001239906,0.0005708003,0.0005157708,0.0002487155,0.000745713,0.001657172,0.0009219767,0.007204906],"category_scores_gemma":[0.00504055,0.0003394925,0.0009213454,0.0004947209,0.0009538888,0.002382874,0.002984506,0.002154372,0.002363016],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006976451,"about_ca_system_score_gemma":0.0007114568,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002701527,"about_ca_topic_score_gemma":0.003883281,"domain_scores_codex":[0.9992383,0.0001505207,0.00003723404,0.0003300073,0.0001719682,0.00007190971],"domain_scores_gemma":[0.9990405,0.0003116321,0.0001121169,0.0003192773,0.0001410972,0.0000753474],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0008612644,0.0006752056,0.004378966,0.0005639558,0.0002321057,0.0003020896,0.0003995298,0.06395005,0.0696888,0.00860512,0.01525381,0.8350891],"study_design_scores_gemma":[0.0002887466,0.00152936,0.01367675,0.0002440786,0.0002735485,0.0008243054,0.000250932,0.7797145,0.1019776,0.06455377,0.03653002,0.0001363416],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1616094,0.002139293,0.8002308,0.001733,0.0005706882,0.0003561667,0.002371869,0.0134544,0.01753429],"genre_scores_gemma":[0.759289,0.0007527656,0.2201442,0.001053175,0.0002407032,0.0004415488,0.003617043,0.0006627883,0.01379873],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007204906,"threshold_uncertainty_score":0.02410287,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03222141815507383,"score_gpt":0.2756459686591374,"score_spread":0.2434245505040636,"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."}}