{"id":"W3164226412","doi":"10.3389/fnins.2021.657958","title":"Deep Cross-User Models Reduce the Training Burden in Myoelectric Control","year":2021,"lang":"en","type":"article","venue":"Frontiers in Neuroscience","topic":"Muscle activation and electromyography studies","field":"Engineering","cited_by":50,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs; New Brunswick Innovation Foundation","keywords":"Computer science; Machine learning; Leverage (statistics); Subject-matter expert; Artificial intelligence; Adaptation (eye); Artificial neural network; Cross-validation; Protocol (science); Expert system","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001937685,0.0001181566,0.0001642112,0.0001909015,0.0001129537,0.00008465954,0.0002781707,0.00003831456,0.000002708816],"category_scores_gemma":[0.000140918,0.0001040105,0.00004309795,0.001699443,0.0001141338,0.0002899563,0.000021942,0.000276948,2.050522e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005694403,"about_ca_system_score_gemma":0.00003751258,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008650702,"about_ca_topic_score_gemma":0.00001546899,"domain_scores_codex":[0.9988652,0.00005242264,0.0001962689,0.0002717061,0.0001890156,0.0004253273],"domain_scores_gemma":[0.999669,0.00005156291,0.00002214671,0.0001933787,0.00002655736,0.00003741658],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001526095,0.00002673039,0.01155677,0.00001706274,0.000008855413,0.00004592907,0.003148695,0.9110542,0.02271372,0.0006629967,0.002073429,0.04867634],"study_design_scores_gemma":[0.0005510173,0.00001752007,0.0746826,0.00001395105,0.00000331453,0.000009056703,0.000486949,0.9187218,0.001246289,0.001367599,0.002720137,0.0001797658],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5172348,0.004656665,0.4642567,0.001511487,0.003372302,0.0004538137,0.000003764583,0.0002566308,0.008253804],"genre_scores_gemma":[0.9984507,0.0003741614,0.0005434164,0.0004259296,0.00003866122,0.00004087208,3.892571e-7,0.00001351726,0.0001123828],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4812159,"threshold_uncertainty_score":0.4241425,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01819548210194328,"score_gpt":0.2343533977357119,"score_spread":0.2161579156337687,"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."}}