{"id":"W3175078852","doi":"10.1609/aaai.v35i1.16168","title":"Riemannian Embedding Banks for Common Spatial Patterns with EEG-based SPD Neural Networks","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"EEG and Brain-Computer Interfaces","field":"Neuroscience","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Ministry of Science and ICT, South Korea; National Research Foundation of Korea; National Research Foundation","keywords":"Embedding; Artificial intelligence; Riemannian geometry; Computer science; Riemannian manifold; Manifold (fluid mechanics); Artificial neural network; Pattern recognition (psychology); Generalization; Deep learning; Nonlinear dimensionality reduction; Feature (linguistics); Feature vector; Context (archaeology); Metric (unit); Mathematics; Algorithm; Pure mathematics; Dimensionality reduction; Mathematical analysis; Geography","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":[],"consensus_categories":[],"category_scores_codex":[0.0002578776,0.0003287919,0.0003819952,0.00008541362,0.0003379277,0.0003948122,0.0010577,0.0001131823,0.0001050187],"category_scores_gemma":[0.0004101878,0.0002369017,0.000172597,0.0003703082,0.0003236107,0.0002294469,0.0002061525,0.0004316231,0.000008553548],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003725217,"about_ca_system_score_gemma":0.00008655916,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005777225,"about_ca_topic_score_gemma":0.0001249191,"domain_scores_codex":[0.997675,0.00004166085,0.0005482225,0.0007384937,0.0004666981,0.0005299136],"domain_scores_gemma":[0.9982804,0.0004248449,0.0004105193,0.0002754612,0.0004941432,0.0001146126],"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":[0.002348756,0.001267361,0.01161896,0.0005837955,0.00006599194,0.00003304656,0.003011166,0.04740516,0.4869261,0.1844064,0.0004592042,0.2618741],"study_design_scores_gemma":[0.00005616122,0.0002953699,0.0001938857,0.0002622754,0.0000156193,0.000009152726,0.0002057039,0.4207717,0.5758455,0.00211097,0.0000474897,0.0001862246],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8868328,0.00001156817,0.106657,0.003626307,0.0007358951,0.0006601021,0.00004068659,0.0001068844,0.001328713],"genre_scores_gemma":[0.9977804,0.000005406603,0.0005314876,0.001288604,0.0001668244,0.00005177038,0.000002674773,0.0000340782,0.0001387637],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3733665,"threshold_uncertainty_score":0.9660573,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0723957588379945,"score_gpt":0.3127454600403223,"score_spread":0.2403497012023278,"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."}}