{"id":"W2949496227","doi":"","title":"Functional Variational Bayesian Neural Networks","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Gaussian Processes and Bayesian Inference","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Prior probability; Infimum and supremum; Estimator; Bayesian probability; Computer science; Gaussian; Applied mathematics; Upper and lower bounds; Mathematical optimization; Artificial neural network; Inference; Mathematics; Divergence (linguistics); Algorithm; Artificial intelligence; Statistics; Physics; Mathematical analysis","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003373057,0.001160415,0.001173874,0.001053563,0.0006241873,0.0019808,0.002333043,0.00252665,0.003354381],"category_scores_gemma":[0.01301276,0.0008239355,0.0008768051,0.001372733,0.002082365,0.002677775,0.001983685,0.002683813,0.0007189627],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001940605,"about_ca_system_score_gemma":0.001764197,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008200032,"about_ca_topic_score_gemma":0.007568242,"domain_scores_codex":[0.9981226,0.001004707,0.00007939124,0.0003299814,0.0003586293,0.0001046346],"domain_scores_gemma":[0.9972376,0.001823089,0.00021182,0.0002478688,0.0003803346,0.00009928257],"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":[0.00003233839,0.00002170703,0.0008095592,0.0001271749,0.00007119255,0.00004924295,0.00008762546,0.3995098,0.0006698545,0.5567064,0.002966372,0.03894879],"study_design_scores_gemma":[0.000005322397,0.00000547415,0.0001148686,0.00002537416,0.000005936249,0.00001876857,0.000008528868,0.7593178,0.0001619655,0.2377366,0.002590041,0.000009260028],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002805488,0.0005466701,0.9929918,0.0004493811,0.00003940029,0.00001998145,0.0001477666,0.0001087014,0.002890764],"genre_scores_gemma":[0.3903821,0.002796828,0.5932783,0.0007562166,0.0003318414,0.0003488666,0.001216658,0.0003508391,0.01053829],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008200032,"threshold_uncertainty_score":0.01783866,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04334265676423611,"score_gpt":0.169924799846442,"score_spread":0.1265821430822058,"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."}}