{"id":"W3046356352","doi":"10.1088/1741-2552/abca18","title":"Uncovering the structure of clinical EEG signals with self-supervised learning","year":2020,"lang":"en","type":"preprint","venue":"Journal of Neural Engineering","topic":"EEG and Brain-Computer Interfaces","field":"Neuroscience","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"InteraXon (Canada)","funders":"Agence Nationale de la Recherche; Mitacs; Canadian Institute for Advanced Research","keywords":"Artificial intelligence; Computer science; Electroencephalography; Deep learning; Machine learning; Supervised learning; Context (archaeology); Artificial neural network; Pattern recognition (psychology); Feature (linguistics); Psychology","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":[0.002730446,0.0008316684,0.0005494742,0.0009870778,0.000261079,0.0007030801,0.0008764255,0.0007110114,0.0005594883],"category_scores_gemma":[0.009409087,0.0003276105,0.0006699779,0.0005257597,0.001089259,0.001040612,0.0009939342,0.001186868,0.0003657742],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004623803,"about_ca_system_score_gemma":0.0008701519,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007565925,"about_ca_topic_score_gemma":0.001382801,"domain_scores_codex":[0.9986135,0.0005966983,0.00006991751,0.0004518842,0.0001972666,0.00007076125],"domain_scores_gemma":[0.9930105,0.003633696,0.001203338,0.001061931,0.0009104431,0.0001802226],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006796349,0.0008639958,0.04277597,0.0005815271,0.0003635843,0.0002611809,0.0004309755,0.4007123,0.0289985,0.004415804,0.00741148,0.5125051],"study_design_scores_gemma":[0.00001018701,0.00006479701,0.002502767,0.00001871813,0.00001111219,0.00003085809,0.00001924483,0.9884239,0.004234556,0.004308262,0.0003659678,0.000009669749],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3029417,0.0009121756,0.6911892,0.000727076,0.00007624267,0.000161467,0.0006161899,0.001657691,0.001718308],"genre_scores_gemma":[0.9221251,0.0001248489,0.07580186,0.0001266745,0.00007240134,0.00009132507,0.0009163746,0.00006934142,0.0006720272],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002730446,"threshold_uncertainty_score":0.01444012,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04065727197530686,"score_gpt":0.2953111873568379,"score_spread":0.254653915381531,"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."}}