{"id":"W4386454182","doi":"10.36244/icj.2023.5.2","title":"Deep Learning from Noisy Labels with Some Adjustments of a Recent Method","year":2023,"lang":"en","type":"article","venue":"Híradástechnika/Infocommunications journal","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"European Social Fund; European Commission; Canadian Institute for Advanced Research","keywords":"Softmax function; Computer science; Extension (predicate logic); Artificial intelligence; Noise (video); Artificial neural network; Pattern recognition (psychology); Function (biology); Machine learning; Image (mathematics)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001408852,0.0001962901,0.0002897175,0.0005223969,0.0006425598,0.0002220241,0.002584812,0.0001052057,0.00007821381],"category_scores_gemma":[0.0003300884,0.0001667733,0.00007982853,0.001662336,0.0000823821,0.0009596978,0.0006451931,0.001054168,0.0001335169],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009888886,"about_ca_system_score_gemma":0.0001444171,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008935296,"about_ca_topic_score_gemma":0.00001976318,"domain_scores_codex":[0.9975538,0.0006604919,0.0006202845,0.0002968051,0.0005393418,0.0003292511],"domain_scores_gemma":[0.9963301,0.0005619446,0.0007227386,0.001907239,0.0003201685,0.0001577976],"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":[0.00004362197,0.0003640315,0.005771565,0.00002812932,0.0002669226,0.0000190956,0.003695901,0.01341935,0.00864351,0.08258668,0.001620075,0.8835411],"study_design_scores_gemma":[0.003110724,0.0007438609,0.09663954,0.0004354349,0.0001735112,0.0004147392,0.001734699,0.5746012,0.003238998,0.02189689,0.2959588,0.001051535],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003568108,0.0008375904,0.98419,0.006539834,0.0001265192,0.0003079154,0.000007596273,0.0006781187,0.003744303],"genre_scores_gemma":[0.1946567,0.006324103,0.7979109,0.0002161918,0.00008883213,0.00009885236,0.0002175522,0.00004312463,0.0004437766],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8824896,"threshold_uncertainty_score":0.6800818,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05406486913937391,"score_gpt":0.3355921552952093,"score_spread":0.2815272861558354,"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."}}