{"id":"W2963371670","doi":"","title":"Learning to Reweight Examples for Robust Deep Learning","year":2018,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":418,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Hyperparameter; Overfitting; Computer science; Artificial intelligence; Machine learning; Regularization (linguistics); Deep learning; Gradient descent; Artificial neural network; Set (abstract data type); Deep neural networks; Supervised learning","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001104122,0.0003417186,0.000283324,0.0004921886,0.0008578479,0.0007642539,0.001607317,0.0001224979,0.0005259847],"category_scores_gemma":[0.002578889,0.0003335354,0.0001183507,0.000404149,0.00007584934,0.0005426779,0.0004260685,0.001086325,0.0007732463],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000122681,"about_ca_system_score_gemma":0.00007525834,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001557361,"about_ca_topic_score_gemma":0.00009606967,"domain_scores_codex":[0.9969825,0.0003782009,0.0004632231,0.001005114,0.0006498792,0.0005210653],"domain_scores_gemma":[0.9978133,0.0004762481,0.0003456253,0.0004376739,0.0007050349,0.0002221146],"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":[0.0002463089,0.0001225345,0.01958715,0.00002736876,0.0001035929,0.00001371009,0.003924772,0.04834091,0.00546048,0.3564731,0.0005340254,0.565166],"study_design_scores_gemma":[0.0004597359,0.0009559785,0.003699543,0.00007376661,0.000007271814,0.000015706,0.0002015639,0.7772194,0.0002924732,0.0009472693,0.2157677,0.0003596274],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01150482,0.0000333766,0.9407945,0.00775772,0.0008638629,0.0003139963,0.000006682665,0.0007742177,0.03795082],"genre_scores_gemma":[0.9147466,0.00004221943,0.07410017,0.0005946079,0.0007036721,0.0000881712,0.0002622531,0.00004621994,0.009416101],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9032418,"threshold_uncertainty_score":0.9999117,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06198251208780124,"score_gpt":0.3196849676050122,"score_spread":0.257702455517211,"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."}}