{"id":"W3041755437","doi":"10.1109/icpr48806.2021.9412478","title":"Batch-Incremental Triplet Sampling for Training Triplet Networks Using Bayesian Updating Theorem","year":2021,"lang":"en","type":"preprint","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Discriminative model; Embedding; Prior probability; Computer science; Bayesian probability; MNIST database; Sampling (signal processing); Gibbs sampling; Subspace topology; Data mining; Artificial intelligence; Hierarchy; Bayesian network; Pattern recognition (psychology); Machine learning; Deep learning; Detector","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":[0.00347515,0.001528027,0.001938231,0.001602195,0.0009439816,0.001186533,0.002946593,0.001576239,0.003624326],"category_scores_gemma":[0.0136594,0.0009755628,0.001577726,0.001886267,0.0009347639,0.002688314,0.001870497,0.003085673,0.001272848],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001402942,"about_ca_system_score_gemma":0.001715651,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007535681,"about_ca_topic_score_gemma":0.01127877,"domain_scores_codex":[0.99821,0.0006257588,0.0001085617,0.0005189832,0.000386131,0.0001506352],"domain_scores_gemma":[0.9953545,0.002540078,0.0003600731,0.0006814959,0.0008588731,0.0002049691],"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":[0.0003770549,0.0003091212,0.004610878,0.0001636951,0.0001727868,0.0001575759,0.0001909044,0.5522848,0.005601442,0.02331529,0.007746129,0.4050703],"study_design_scores_gemma":[0.000006662017,0.00002064715,0.0001281835,0.000004448454,0.000007335744,0.00001911515,0.000005727703,0.9926687,0.0005914572,0.00622845,0.0003136996,0.000005459828],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007483254,0.0001124568,0.9908196,0.0001046429,0.00002676921,0.00007374522,0.0001155693,0.0007600227,0.0005040093],"genre_scores_gemma":[0.351501,0.0002591354,0.6418269,0.0004131687,0.0001364099,0.0005938679,0.002026471,0.0004128471,0.002830049],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007535681,"threshold_uncertainty_score":0.01837856,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09326980976450137,"score_gpt":0.3227602744669691,"score_spread":0.2294904647024677,"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."}}