{"id":"W2994411342","doi":"","title":"Apprentissage de représentations auto-supervisé à partir de signaux d'électroencéphalographie","year":2019,"lang":"fr","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"EEG and Brain-Computer Interfaces","field":"Neuroscience","cited_by":63,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institut National de la Recherche Scientifique; InteraXon (Canada)","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning; Electroencephalography; Supervised learning; Task (project management); Context (archaeology); Exploit; Representation (politics); Feature learning; Feature (linguistics); Semi-supervised learning; Pattern recognition (psychology); Artificial neural network","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","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.005768471,0.0007824168,0.0007366196,0.0004342259,0.001092488,0.001621466,0.003267446,0.0006031398,0.0007146065],"category_scores_gemma":[0.00236893,0.0008993992,0.000674572,0.001154378,0.001330398,0.0004477495,0.002054134,0.001648653,0.0003716778],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003490113,"about_ca_system_score_gemma":0.0008552318,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001528704,"about_ca_topic_score_gemma":0.001021779,"domain_scores_codex":[0.9801338,0.01448195,0.001113483,0.002075266,0.0007453732,0.001450102],"domain_scores_gemma":[0.9894055,0.004390921,0.0008221325,0.003577706,0.001227003,0.0005767676],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00005968146,0.003538226,0.02211395,0.0009301386,0.0003243067,0.0001279817,0.07226476,0.004620347,0.6212155,0.2211408,0.01226394,0.04140032],"study_design_scores_gemma":[0.001050732,0.000004271158,0.013268,0.003014557,0.0002166379,0.000237609,0.0005947586,0.1676727,0.764376,0.01081576,0.03752078,0.001228239],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5808653,0.001605155,0.352547,0.0237155,0.00126961,0.001052067,0.0001918601,0.0004917352,0.0382618],"genre_scores_gemma":[0.929775,0.001578685,0.03472215,0.0006602038,0.00009595319,0.0001691906,0.0002677721,0.0001172736,0.03261377],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3489097,"threshold_uncertainty_score":0.9994149,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02148435684519823,"score_gpt":0.2690009049247138,"score_spread":0.2475165480795156,"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."}}