{"id":"W3204409915","doi":"10.1109/icassp43922.2022.9746528","title":"Holistic Semi-Supervised Approaches for EEG Representation Learning","year":2022,"lang":"en","type":"article","venue":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","topic":"EEG and Brain-Computer Interfaces","field":"Neuroscience","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Electroencephalography; Artificial intelligence; Computer science; Machine learning; Class (philosophy); Task (project management); Supervised learning; Representation (politics); Pattern recognition (psychology); Semi-supervised learning; Field (mathematics); Artificial neural network; Mathematics; Psychology; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00246927,0.001937378,0.001758995,0.001306156,0.0004972768,0.0009814332,0.002633998,0.001295214,0.002203865],"category_scores_gemma":[0.005654619,0.000564008,0.001237172,0.001321642,0.0009189975,0.001719213,0.002242082,0.001761163,0.00139702],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004116734,"about_ca_system_score_gemma":0.0007323829,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009292251,"about_ca_topic_score_gemma":0.001807756,"domain_scores_codex":[0.9974842,0.0008665879,0.0001341409,0.0008654737,0.0005209612,0.000128635],"domain_scores_gemma":[0.9965205,0.001149173,0.0003978332,0.0009870352,0.000816407,0.0001290523],"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":[0.0003617288,0.0003666644,0.002378614,0.0004882878,0.0005411148,0.0001313388,0.000197691,0.1980461,0.0170251,0.005420559,0.008513286,0.7665294],"study_design_scores_gemma":[0.00001598004,0.0001106076,0.0006982177,0.00001647353,0.00004226016,0.0001165005,0.00004140604,0.9845679,0.004656381,0.008319722,0.001394459,0.00001997266],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008233068,0.0003947488,0.9894713,0.00006679962,0.00003168167,0.0000614672,0.0001232093,0.001076179,0.0005414546],"genre_scores_gemma":[0.3992669,0.0006083614,0.5926883,0.0003176995,0.0002572458,0.0004926106,0.002389439,0.0004609862,0.003518365],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002633998,"threshold_uncertainty_score":0.0130589,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1683268527922888,"score_gpt":0.3447223670880592,"score_spread":0.1763955142957704,"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."}}