{"id":"W7056781305","doi":"","title":"Fully Bayesian learning and classic deep learning: An efficient unified method for estimating uncertainty","year":2020,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Magnetic Field Sensors Techniques","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"McGill University","keywords":"Bayesian probability; Deep learning; Feature (linguistics); Bayesian inference; Noise (video); Stability (learning theory); Set (abstract data type)","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":[0.004395453,0.001491848,0.001466616,0.001815737,0.0005475429,0.002311024,0.002612542,0.00183993,0.003742374],"category_scores_gemma":[0.01370146,0.001267809,0.00142401,0.001739475,0.002375642,0.004098191,0.003579593,0.003762893,0.001016663],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002337517,"about_ca_system_score_gemma":0.002719123,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005991758,"about_ca_topic_score_gemma":0.006115322,"domain_scores_codex":[0.9968964,0.001241411,0.0001406218,0.0004363783,0.001149528,0.0001357452],"domain_scores_gemma":[0.9967699,0.001978565,0.0002587822,0.0003788498,0.0005067327,0.0001070633],"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":[0.00005802255,0.00004222265,0.0006042399,0.0002000712,0.0001063059,0.00006484598,0.0001241582,0.3435684,0.001593067,0.4995089,0.004682074,0.1494477],"study_design_scores_gemma":[0.000006771333,0.00001515202,0.0001281431,0.00004581663,0.00001268349,0.00003553611,0.000008693552,0.8387187,0.0007574329,0.1563918,0.003857195,0.00002217695],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0003633241,0.0002023584,0.9985461,0.0001295425,0.00001625392,0.000009005469,0.00003228306,0.00006902881,0.0006321323],"genre_scores_gemma":[0.1071121,0.00215617,0.8826876,0.0003769081,0.0003396726,0.0003068055,0.0003462853,0.0003301092,0.006344198],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005991758,"threshold_uncertainty_score":0.02324569,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01239164799930028,"score_gpt":0.2626198046691368,"score_spread":0.2502281566698366,"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."}}