{"id":"W6980662860","doi":"","title":"Comparing Uncertainty Estimation Methods in Deep Neural Networks","year":2023,"lang":"en","type":"other","venue":"Sabanci University","topic":"Canadian Policy and Governance","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institute for Advanced Research","keywords":"Softmax function; Convolutional neural network; Artificial neural network; Deep learning; Uncertainty quantification; Deep neural networks; Monte Carlo method","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01358988,0.002505349,0.001471904,0.003207474,0.0009560251,0.002628733,0.002760855,0.00258204,0.001204684],"category_scores_gemma":[0.04699832,0.0006917043,0.001215236,0.001576515,0.001456511,0.00541894,0.003935175,0.003328612,0.0004081336],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003351081,"about_ca_system_score_gemma":0.002325135,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01749635,"about_ca_topic_score_gemma":0.0143149,"domain_scores_codex":[0.9940784,0.002396875,0.0004591055,0.001101435,0.001639722,0.0003245233],"domain_scores_gemma":[0.9786133,0.01585457,0.001063498,0.001689194,0.002445133,0.0003343405],"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":[0.001062815,0.0002689365,0.01365072,0.0005371326,0.0005519617,0.00009801241,0.0001901925,0.7538798,0.000686197,0.01681295,0.009793174,0.2024681],"study_design_scores_gemma":[0.00002954256,0.00009134146,0.00146451,0.00009450725,0.00004206804,0.00002802162,0.00005854143,0.9838746,0.001025335,0.01209649,0.001170276,0.00002484447],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3614033,0.03043645,0.5742459,0.007007728,0.001415593,0.0005108482,0.003639433,0.00409361,0.01724707],"genre_scores_gemma":[0.877029,0.005122254,0.1067911,0.0008617778,0.0005607832,0.0002674533,0.006352703,0.0003964216,0.002618444],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01749635,"threshold_uncertainty_score":0.07187098,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0361877601179063,"score_gpt":0.3270748956706776,"score_spread":0.2908871355527713,"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."}}