{"id":"W2964096266","doi":"","title":"Toward Robustness against Label Noise in Training Deep Discriminative Neural Networks","year":2017,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":186,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Robustness (evolution); Discriminative model; Artificial intelligence; Inference; Convolutional neural network; Deep neural networks; Pattern recognition (psychology); Machine learning; Noise (video); Training set; Graphical model; Artificial neural network; Noise measurement; Image (mathematics); Noise reduction","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006086789,0.0002028384,0.000244983,0.0001965169,0.0006990519,0.003048989,0.001214363,0.0001045212,7.907429e-7],"category_scores_gemma":[0.0002841445,0.0001769943,0.00003322319,0.0002360636,0.00007036065,0.01052667,0.0001965389,0.0003786645,0.000008833825],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007466594,"about_ca_system_score_gemma":0.00005695038,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000103772,"about_ca_topic_score_gemma":0.00001734681,"domain_scores_codex":[0.9983118,0.0001160437,0.0006100682,0.0002586684,0.0003444012,0.0003589827],"domain_scores_gemma":[0.9982266,0.00004947923,0.0008543229,0.0005851656,0.0001892288,0.00009523325],"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":[0.000009880215,0.00001821094,0.001296918,0.0001924239,0.000003105962,0.000004933349,0.008231872,0.3069628,0.00001615895,0.001916328,0.00004880345,0.6812985],"study_design_scores_gemma":[0.0004935086,0.00002501046,0.01094786,0.000140525,0.000003107405,0.0000215644,0.001082957,0.9866949,0.000005161824,0.00001324253,0.0003617607,0.0002104245],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05892183,0.0001890202,0.932761,0.001877015,0.001246889,0.0003761209,0.000004161994,0.0003243214,0.004299708],"genre_scores_gemma":[0.998104,0.000007067553,0.001363933,0.0002121229,0.0001182733,0.00006036638,0.00007394577,0.000008929559,0.00005131482],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9391822,"threshold_uncertainty_score":0.997986,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0666042164439337,"score_gpt":0.2991574030539693,"score_spread":0.2325531866100355,"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."}}