{"id":"W3162818615","doi":"10.1109/icpr48806.2021.9412478","title":"Batch-Incremental Triplet Sampling for Training Triplet Networks Using Bayesian Updating Theorem","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Discriminative model; Embedding; Computer science; Prior probability; Bayesian probability; MNIST database; Sampling (signal processing); Bayesian network; Artificial intelligence; Gibbs sampling; Data mining; Subspace topology; Machine learning; Pattern recognition (psychology); 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":[0.003442225,0.001560958,0.001985361,0.001590019,0.0009785719,0.001181074,0.003003926,0.001601601,0.003672406],"category_scores_gemma":[0.01372442,0.001002854,0.001603907,0.001891942,0.0009401114,0.00271013,0.00191281,0.003122553,0.001291859],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001427318,"about_ca_system_score_gemma":0.001790317,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00795444,"about_ca_topic_score_gemma":0.01219048,"domain_scores_codex":[0.9981773,0.0006387492,0.0001122137,0.0005325396,0.0003857632,0.0001534769],"domain_scores_gemma":[0.9952796,0.002575049,0.0003721936,0.0006810639,0.0008831148,0.000209059],"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":[0.0003741208,0.0003164515,0.004834217,0.0001601662,0.0001727391,0.000162666,0.0001931503,0.5598581,0.005322448,0.02204943,0.008114305,0.3984421],"study_design_scores_gemma":[0.000006983804,0.00002097873,0.000128468,0.000004585519,0.000007468508,0.00001926913,0.000006036035,0.992819,0.0005677126,0.006103178,0.0003106341,0.000005549642],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008049841,0.0001155244,0.990172,0.000114013,0.00002881133,0.00007608298,0.0001242519,0.000800948,0.0005185067],"genre_scores_gemma":[0.3615647,0.0002554555,0.6315912,0.0004365295,0.0001393289,0.0006058792,0.002168452,0.000422646,0.002815803],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00795444,"threshold_uncertainty_score":0.01820445,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1955585632772747,"score_gpt":0.2394912117054368,"score_spread":0.04393264842816205,"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."}}