{"id":"W4390414985","doi":"10.1016/j.neucom.2023.127183","title":"Analytically tractable heteroscedastic uncertainty quantification in Bayesian neural networks for regression tasks","year":2023,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Gaussian Processes and Bayesian Inference","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Homoscedasticity; Heteroscedasticity; Inference; Computer science; Covariate; Bayesian probability; Artificial neural network; Gaussian; Bayesian inference; Gaussian process; Artificial intelligence; Predictive inference; Regression; Mathematics; Uncertainty quantification; Machine learning; Statistics; Frequentist inference","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":[0.0004564515,0.0002108573,0.0002539568,0.0002534131,0.0002455769,0.0003515629,0.000795605,0.00009672243,0.00000202496],"category_scores_gemma":[0.0001633152,0.0001885837,0.00008838215,0.001504012,0.00003094585,0.0003730446,0.0002062705,0.000278821,0.00001028532],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003551326,"about_ca_system_score_gemma":0.00005084367,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001656945,"about_ca_topic_score_gemma":0.00001533635,"domain_scores_codex":[0.9978237,0.00008172398,0.0004810666,0.0007227658,0.0002267336,0.0006639783],"domain_scores_gemma":[0.9986984,0.0004751336,0.0001853668,0.0004376557,0.0000847588,0.0001187246],"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":[0.00003655831,0.0001074969,0.005378203,0.0001732552,0.000007865253,0.000066815,0.0003460812,0.6748033,0.001706193,0.01508094,0.0005736632,0.3017197],"study_design_scores_gemma":[0.0003136251,0.00008504881,0.01514745,0.00009079255,0.000003865387,0.00001138886,0.00001471872,0.9814946,0.000114809,0.002415068,0.0001152841,0.0001933193],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04835664,0.00001898579,0.9490628,0.001260075,0.000449525,0.0003428764,0.00000136485,0.0003736954,0.0001340568],"genre_scores_gemma":[0.991918,0.000005601529,0.007560627,0.0002889265,0.0001213976,0.00003121523,0.0000142075,0.00001992756,0.00004008287],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9435614,"threshold_uncertainty_score":0.7690222,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03047839580974849,"score_gpt":0.2947843967770761,"score_spread":0.2643060009673276,"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."}}