{"id":"W2990179544","doi":"10.1007/s00500-019-04567-2","title":"A new hybrid discriminative/generative model using the full-covariance multivariate generalized Gaussian mixture models","year":2019,"lang":"en","type":"article","venue":"Soft Computing","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Discriminative model; Fisher kernel; Artificial intelligence; Pattern recognition (psychology); Computer science; Covariance; Machine learning; Kernel (algebra); Model selection; Mixture model; Gaussian process; Markov chain Monte Carlo; Generative model; Support vector machine; Marginal likelihood; Gaussian; Mathematics; Kernel Fisher discriminant analysis; Bayesian probability; Facial recognition system; Generative grammar; Statistics","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"],"consensus_categories":[],"category_scores_codex":[0.0009287154,0.0004800176,0.0005293672,0.0001139806,0.0005507807,0.0004700389,0.001602108,0.0001219403,0.00001069251],"category_scores_gemma":[0.0000475416,0.0003407781,0.0002293555,0.0004963874,0.00006003328,0.0008527903,0.0008175476,0.0005473485,0.00001447972],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001119102,"about_ca_system_score_gemma":0.0003913101,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001759442,"about_ca_topic_score_gemma":0.000006313253,"domain_scores_codex":[0.996668,0.0005158044,0.000506981,0.001056843,0.0004765454,0.0007758259],"domain_scores_gemma":[0.9978774,0.0002429245,0.0003523914,0.001140499,0.0001707765,0.0002160402],"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":[0.00001889651,0.0000290418,0.000005455817,0.00001876117,0.00005991257,0.00001363132,0.005535369,0.6204941,0.01636255,0.3155803,0.000350976,0.04153099],"study_design_scores_gemma":[0.0006417445,0.00002946179,0.000007452304,0.00007938277,0.00002224834,0.00005429371,0.00002465018,0.8018436,0.002869993,0.1939821,0.0000540765,0.0003909722],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01087344,0.0003698708,0.9847274,0.001323481,0.0008084863,0.0006025392,0.000007173059,0.0002298017,0.001057783],"genre_scores_gemma":[0.3447553,0.000003562011,0.653617,0.0008123705,0.000247294,0.000003659196,0.000002932171,0.00003229837,0.0005256354],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3338818,"threshold_uncertainty_score":0.9999044,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04143502068957534,"score_gpt":0.3000837096003409,"score_spread":0.2586486889107656,"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."}}