{"id":"W3036503133","doi":"10.1109/icccs49078.2020.9118568","title":"Optimal Training Data Selection in Active Learning for Discrimination and Classification","year":2020,"lang":"en","type":"article","venue":"2020 5th International Conference on Computer and Communication Systems (ICCCS)","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Brock University","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning; Classifier (UML); Active learning (machine learning); Monte Carlo method; Learning classifier system; Pattern recognition (psychology); Unsupervised learning; Mathematics; Statistics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004844842,0.0001543382,0.0001983088,0.0001182508,0.000203333,0.000530419,0.001016129,0.00006757139,0.000004806907],"category_scores_gemma":[0.00009491139,0.0001567278,0.00002148615,0.0001900064,0.00003847286,0.0007276945,0.0004722951,0.000358008,0.000005255496],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004355194,"about_ca_system_score_gemma":0.00005757237,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005401731,"about_ca_topic_score_gemma":0.00001240711,"domain_scores_codex":[0.9984244,0.000297471,0.0003438816,0.0005508116,0.0002397421,0.0001437674],"domain_scores_gemma":[0.9989675,0.0002241689,0.0002336232,0.0002939766,0.0001932396,0.00008745855],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001284725,0.0001084574,0.002312446,0.00009239902,0.00009250998,0.000002096833,0.0168685,0.01509633,0.0007343894,0.4238413,0.0007629741,0.5399601],"study_design_scores_gemma":[0.0005653605,0.0001635473,0.009014576,0.0001068663,0.000005292036,0.00001285677,0.0008665444,0.9847023,0.000008915948,0.0002600123,0.004134773,0.0001589088],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01717964,0.00009596806,0.9691318,0.01158802,0.0002260037,0.0003727614,0.00001646325,0.0001346111,0.001254719],"genre_scores_gemma":[0.9693558,0.0001678275,0.02969245,0.0002276394,0.0001823044,0.00006070479,0.0002296224,0.00001025575,0.00007343195],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.969606,"threshold_uncertainty_score":0.6391173,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1957910737432852,"score_gpt":0.3599655975664877,"score_spread":0.1641745238232025,"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."}}