{"id":"W4391230394","doi":"10.1007/s12065-023-00900-9","title":"Gaussian mixture models for training Bayesian convolutional neural networks","year":2024,"lang":"en","type":"article","venue":"Evolutionary Intelligence","topic":"Gaussian Processes and Bayesian Inference","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec à Rimouski","funders":"","keywords":"Computer science; Convolutional neural network; Machine learning; Artificial intelligence; Training (meteorology); Bayesian probability; Gaussian process; Gaussian; Mixture model; Training set; Pattern recognition (psychology)","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":[0.0002828299,0.0003238201,0.0002421654,0.0002099299,0.0003870754,0.0004081344,0.00124141,0.0002599539,0.00009135246],"category_scores_gemma":[0.00004443448,0.0002978053,0.000220723,0.0008588915,0.0001713251,0.001653948,0.0001783196,0.000547916,0.00004108835],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001313236,"about_ca_system_score_gemma":0.0003932856,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000132194,"about_ca_topic_score_gemma":0.000007849867,"domain_scores_codex":[0.9974799,0.00005030625,0.0004733027,0.00089849,0.0003828915,0.0007151053],"domain_scores_gemma":[0.9987459,0.0003184439,0.00007573321,0.0004570277,0.000173436,0.0002294256],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001055461,0.00002969838,0.00001511828,0.00007227552,0.00002926249,0.00003084734,0.0007335199,0.08493823,0.0000139511,0.8319663,0.00381647,0.07834379],"study_design_scores_gemma":[0.00003477397,0.00008150643,0.00006704963,0.00011997,0.00000901602,0.0001705246,0.00006879783,0.7280142,0.00002482738,0.2674453,0.003685148,0.0002788929],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0000280017,0.007382391,0.9828636,0.004703636,0.001870098,0.0003303137,0.00003444777,0.0005623687,0.002225116],"genre_scores_gemma":[0.9042671,0.000118664,0.09375313,0.0005073074,0.0005350507,0.0001322742,0.00002954261,0.00002599119,0.0006309036],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9042391,"threshold_uncertainty_score":0.9999474,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03253978695410235,"score_gpt":0.2700905110650882,"score_spread":0.2375507241109858,"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."}}