{"id":"W3033862284","doi":"10.1109/icmla51294.2020.00180","title":"Learning across label confidence distributions using Filtered Transfer Learning","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; Princess Margaret Cancer Centre; University of Toronto; University Health Network","funders":"Mitacs","keywords":"Transfer of learning; Computer science; Machine learning; Artificial intelligence; Task (project management); Artificial neural network; Deep learning; Retraining; Range (aeronautics); Low Confidence; Meta learning (computer science)","routes":{"ca_aff":true,"ca_fund":true,"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":[0.01331961,0.001752911,0.001519792,0.003072298,0.001063041,0.002937195,0.004258366,0.003644601,0.002359031],"category_scores_gemma":[0.05449298,0.0007844301,0.001845595,0.002049069,0.002759008,0.006115424,0.004483746,0.006170615,0.0009446163],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003667963,"about_ca_system_score_gemma":0.001856404,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005610077,"about_ca_topic_score_gemma":0.004045792,"domain_scores_codex":[0.995262,0.001716311,0.000286252,0.001389842,0.000960438,0.0003850487],"domain_scores_gemma":[0.9708015,0.01858735,0.002403466,0.004518492,0.003087397,0.0006018872],"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":[0.0005877264,0.0005237825,0.01455461,0.0001509,0.0002589754,0.0002571959,0.0003367177,0.7224264,0.003309987,0.01601641,0.003370208,0.2382071],"study_design_scores_gemma":[0.00002067358,0.00006034562,0.0007085859,0.0000144363,0.00001006398,0.00002488659,0.00001919828,0.9761668,0.001578441,0.02114405,0.0002393122,0.00001311202],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08522539,0.0002395315,0.9090319,0.0007081099,0.00004306642,0.0001478476,0.0004090965,0.002820497,0.001374553],"genre_scores_gemma":[0.8454978,0.0001499721,0.1485831,0.0004656419,0.0001119464,0.0003773268,0.002127774,0.000268897,0.002417437],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01331961,"threshold_uncertainty_score":0.07044166,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08604629868095026,"score_gpt":0.3459375196527729,"score_spread":0.2598912209718227,"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."}}