{"id":"W4367187170","doi":"10.1016/j.neuroimage.2023.120142","title":"Unsupervised representation learning of spontaneous MEG data with nonlinear ICA","year":2023,"lang":"en","type":"article","venue":"NeuroImage","topic":"Neural dynamics and brain function","field":"Neuroscience","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Academy of Finland; European Research Council; Canadian Institute for Advanced Research","keywords":"Magnetoencephalography; Computer science; Independent component analysis; Artificial intelligence; Pattern recognition (psychology); Unsupervised learning; Decoding methods; Generalizability theory; Representation (politics); Machine learning; Speech recognition; Electroencephalography; Psychology; Neuroscience","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001280322,0.00010436,0.0001324014,0.000107424,0.0001125808,0.00004281363,0.0003583275,0.00002669505,0.00003622587],"category_scores_gemma":[0.0008010765,0.00008771642,0.00002617404,0.0007394064,0.00007603295,0.0002553971,0.0002147567,0.0001971784,0.00008711938],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006464171,"about_ca_system_score_gemma":0.0000224739,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002676516,"about_ca_topic_score_gemma":0.000008636446,"domain_scores_codex":[0.9986107,0.0001409806,0.0001770209,0.0005416228,0.0003353795,0.0001943091],"domain_scores_gemma":[0.9988576,0.0003553405,0.00009369648,0.0006140498,0.00003280053,0.00004647744],"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":[0.0001316496,0.00003532719,0.0007815312,0.00002126311,0.000002165109,0.001202658,0.000057985,0.00176516,0.9914216,0.00009238813,0.0003215488,0.004166724],"study_design_scores_gemma":[0.001053057,0.0007549548,0.02458591,0.00003591488,0.00003511418,0.0008105211,0.0001026125,0.851678,0.1110301,0.0001031455,0.009488498,0.0003221916],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9965931,0.000001824728,0.0002012917,0.0005064049,0.0001713224,0.0001785897,0.00005433417,0.0002265247,0.0020666],"genre_scores_gemma":[0.9977619,0.00005076287,0.0002049392,0.0002353425,0.00005565145,0.000003318713,0.0001204926,0.00003095033,0.001536623],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8803915,"threshold_uncertainty_score":0.3576972,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07277255043737878,"score_gpt":0.3034520202294717,"score_spread":0.2306794697920929,"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."}}