{"id":"W3123796542","doi":"10.3389/fnhum.2021.653659","title":"BENDR: Using Transformers and a Contrastive Self-Supervised Learning Task to Learn From Massive Amounts of EEG Data","year":2021,"lang":"en","type":"preprint","venue":"Frontiers in Human Neuroscience","topic":"EEG and Brain-Computer Interfaces","field":"Neuroscience","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"St. Michael's Hospital; Vector Institute; University of Toronto","funders":"Electronics and Telecommunications Research Institute; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Electroencephalography; Artificial intelligence; Transformer; Raw data; Leverage (statistics); Variety (cybernetics); Brain–computer interface; Machine learning; Task (project management); Inference; Labeled data; Speech recognition; Pattern recognition (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":[0.004008517,0.001586348,0.0007155901,0.001005334,0.0003837248,0.001115568,0.00252743,0.001719751,0.005321187],"category_scores_gemma":[0.009441407,0.0007081237,0.001066641,0.0006411123,0.000912539,0.002682595,0.002670462,0.002839274,0.003278563],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007156371,"about_ca_system_score_gemma":0.001063385,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002579561,"about_ca_topic_score_gemma":0.004034763,"domain_scores_codex":[0.9988956,0.0004046235,0.0000732902,0.0003779461,0.0001712729,0.00007724544],"domain_scores_gemma":[0.9977277,0.001046786,0.0001525432,0.0005338895,0.0004218213,0.0001171227],"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":[0.001008773,0.000687015,0.003688977,0.0004746682,0.0002865962,0.0002699312,0.0002399106,0.2357372,0.02975105,0.01928236,0.01808802,0.6904855],"study_design_scores_gemma":[0.00004398098,0.0001144041,0.0002604511,0.00001246973,0.00001082317,0.00004478226,0.00001694992,0.9842808,0.005156113,0.008862582,0.001184092,0.00001248138],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01659277,0.00013454,0.9735523,0.000256989,0.00009173454,0.000181754,0.0003178739,0.007429071,0.001442883],"genre_scores_gemma":[0.4121141,0.0002104937,0.5738315,0.0006247374,0.0001167817,0.0006693702,0.003138249,0.001389546,0.007905212],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005321187,"threshold_uncertainty_score":0.02119929,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05303828779676278,"score_gpt":0.2995327502607941,"score_spread":0.2464944624640313,"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."}}