{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001768972,0.00009397403,0.00008530374,0.00004370918,0.0001333724,0.000141307,0.0003867616,0.0000544627,0.0000910209],"category_scores_gemma":[0.0000714866,0.00005362626,0.00001554197,0.0002198941,0.00002792046,0.000511492,0.0000969547,0.0001078169,0.0001309173],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002280285,"about_ca_system_score_gemma":0.00002005988,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007446702,"about_ca_topic_score_gemma":0.00003875147,"domain_scores_codex":[0.9990595,0.0001112033,0.0001247433,0.0003558267,0.0001801235,0.0001686069],"domain_scores_gemma":[0.9991737,0.0001339256,0.00009485608,0.0004732191,0.00006111705,0.00006317623],"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":[0.00001766727,0.00003859728,0.08103498,0.000002690536,0.00002569161,0.000005178054,0.0003058841,0.004294148,0.002811102,0.132617,0.0005612408,0.7782859],"study_design_scores_gemma":[0.0005430392,0.0001260399,0.03401051,0.0000405319,0.000007513262,0.000004177228,0.0000197313,0.9482796,0.0004986901,0.001593956,0.01464716,0.0002290657],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004546989,0.00002593495,0.98796,0.002414839,0.00007949709,0.00005421255,5.023887e-7,0.0003795768,0.004538413],"genre_scores_gemma":[0.9369693,0.00001856675,0.05679974,0.0001734768,0.0001034298,0.000006248518,0.00003649425,0.00001017931,0.00588255],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9439855,"threshold_uncertainty_score":0.2186815,"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."}}