{"id":"W2964273174","doi":"10.1109/icdm.2016.0121","title":"Learning Deep Networks from Noisy Labels with Dropout Regularization","year":2016,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":188,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institute for Advanced Research; National Science Foundation","keywords":"Softmax function; Dropout (neural networks); Computer science; Artificial intelligence; MNIST database; Regularization (linguistics); Stochastic gradient descent; Deep neural networks; Deep learning; Artificial neural network; Noise (video); Machine learning; Pattern recognition (psychology); Gradient descent; Underdetermined system; Algorithm","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":[0.004124372,0.002165323,0.001639591,0.0009457637,0.0008925131,0.001659548,0.002915758,0.002500703,0.001529895],"category_scores_gemma":[0.01551701,0.001054913,0.0008838262,0.001124127,0.001737772,0.003890995,0.002879795,0.004595137,0.0009535739],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002361618,"about_ca_system_score_gemma":0.001866254,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007111995,"about_ca_topic_score_gemma":0.01228655,"domain_scores_codex":[0.9986945,0.0004889708,0.00006538151,0.0002915215,0.0003052526,0.0001544891],"domain_scores_gemma":[0.9959649,0.002192337,0.0004638798,0.0006592741,0.0005818657,0.0001376963],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003050747,0.0001356306,0.002340259,0.0001361134,0.00009135314,0.0001402643,0.0001610004,0.8435615,0.002540585,0.01442457,0.00755156,0.1286121],"study_design_scores_gemma":[0.000008853637,0.00001491993,0.00008241028,0.000009683878,0.000004512789,0.000006790237,0.000005948662,0.9897774,0.0006434848,0.009187313,0.000254511,0.000004159129],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04716791,0.0005016171,0.9469503,0.0008528848,0.00008484699,0.00007058173,0.0002931016,0.002577137,0.001501661],"genre_scores_gemma":[0.7204784,0.0005881925,0.2679587,0.0009633003,0.0002158867,0.0004740025,0.002429316,0.0004159714,0.006476248],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007111995,"threshold_uncertainty_score":0.02181202,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00550017393021877,"score_gpt":0.2010668505581302,"score_spread":0.1955666766279114,"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."}}