{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005556158,0.001567866,0.001132637,0.00162221,0.0009890986,0.001686962,0.002656261,0.002395226,0.002735987],"category_scores_gemma":[0.007230799,0.0006828142,0.001489165,0.001049506,0.001522089,0.003280987,0.003557883,0.005117428,0.001235226],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001222027,"about_ca_system_score_gemma":0.0009911801,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002184841,"about_ca_topic_score_gemma":0.002810878,"domain_scores_codex":[0.9973459,0.0008643585,0.0001640608,0.0007827618,0.0006935686,0.0001493186],"domain_scores_gemma":[0.9975501,0.0006476362,0.00008877733,0.0009313607,0.0006468903,0.0001351782],"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":[0.0003554215,0.0003136482,0.002591299,0.0004161679,0.0005150872,0.0004239121,0.0003220402,0.1342402,0.03154203,0.1204677,0.01472137,0.6940911],"study_design_scores_gemma":[0.00006177392,0.0001715937,0.0007949463,0.00007018819,0.00009822873,0.0004918669,0.00003680937,0.8911459,0.01910061,0.06363466,0.02432541,0.00006800823],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002813116,0.0004284132,0.9942082,0.0003774029,0.0002155452,0.00003525175,0.00006124168,0.0006561047,0.001204695],"genre_scores_gemma":[0.09014469,0.0005608378,0.8994122,0.0007704779,0.0004853248,0.0002407736,0.0004206464,0.0004707475,0.007494361],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005556158,"threshold_uncertainty_score":0.02938408,"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."}}