{"id":"W4382202917","doi":"10.1609/aaai.v37i9.26264","title":"USDNL: Uncertainty-Based Single Dropout in Noisy Label Learning","year":2023,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Wuhan University; National Natural Science Foundation of China","keywords":"Computer science; Dropout (neural networks); Machine learning; Artificial intelligence; Entropy (arrow of time); Computation; Artificial neural network; Cross entropy; Overhead (engineering); Deep neural networks; Selection (genetic algorithm); Algorithm; Pattern recognition (psychology)","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":[0.0009740129,0.000200329,0.000234761,0.0003328563,0.0002050332,0.0002790343,0.00177182,0.00009419033,0.00003120422],"category_scores_gemma":[0.001230177,0.0001611145,0.0000707473,0.001926721,0.0001697915,0.0003259391,0.0003149734,0.0005233882,0.0003232278],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007274436,"about_ca_system_score_gemma":0.0001167049,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001564677,"about_ca_topic_score_gemma":0.00004951562,"domain_scores_codex":[0.9979813,0.00005156801,0.0005027947,0.0005562629,0.000507248,0.0004008184],"domain_scores_gemma":[0.9987153,0.0002065267,0.0003423408,0.0003331535,0.0003292375,0.00007338158],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006350002,0.0002231797,0.005710762,0.00007259072,0.000007384115,0.000001802426,0.001601875,0.005585551,0.1009613,0.7194287,0.0002324381,0.166111],"study_design_scores_gemma":[0.00005943537,0.0002162084,0.001260837,0.0002306941,0.000004469999,0.000001112708,0.0004704657,0.8738568,0.09238393,0.03046624,0.0008194153,0.0002304134],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8798957,0.00002854509,0.05787459,0.03091299,0.0009991261,0.0009425808,0.00001096224,0.001204424,0.02813103],"genre_scores_gemma":[0.9975597,0.00001322599,0.00168666,0.0001665117,0.00003791792,0.000027706,0.000004971596,0.00001390739,0.0004894562],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8682712,"threshold_uncertainty_score":0.657006,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1059308439431945,"score_gpt":0.3191468016734711,"score_spread":0.2132159577302766,"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."}}