{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004736567,0.0009229761,0.001247687,0.001085723,0.0006704777,0.001670004,0.002010689,0.001781707,0.001387462],"category_scores_gemma":[0.01229655,0.000546738,0.000752038,0.0008930571,0.001689577,0.002601558,0.001532153,0.001651226,0.0005761783],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006171095,"about_ca_system_score_gemma":0.0007987482,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007232657,"about_ca_topic_score_gemma":0.0007856603,"domain_scores_codex":[0.9980263,0.0008652807,0.0001018872,0.000374915,0.0004766648,0.0001549889],"domain_scores_gemma":[0.99141,0.006786631,0.000407993,0.0004558515,0.0008027996,0.0001367303],"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":[0.0008718959,0.0007259063,0.003327088,0.0003526921,0.0001040896,0.0002149672,0.0004019022,0.4388255,0.02642927,0.03439478,0.001820781,0.4925311],"study_design_scores_gemma":[0.00001971994,0.0001027616,0.0002076784,0.00001659447,0.00001160243,0.00003620582,0.00002133407,0.9857818,0.006066764,0.007251922,0.0004718872,0.00001168186],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01376594,0.0002259838,0.9851972,0.0001135017,0.00002100135,0.00004155855,0.00001227653,0.0001252482,0.0004971499],"genre_scores_gemma":[0.599471,0.0003431254,0.3972733,0.0002201712,0.0001055888,0.0003629186,0.0001076337,0.00007980114,0.002036382],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004736567,"threshold_uncertainty_score":0.02504969,"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."}}