{"id":"W2895435696","doi":"10.1109/access.2018.2872698","title":"Understanding Mixup Training Methods","year":2018,"lang":"en","type":"article","venue":"IEEE Access","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":105,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Taishan University; Shandong University; Amazon Web Services; National Natural Science Foundation of China; Canadian Institute for Advanced Research","keywords":"Computer science; Machine learning; Artificial neural network; Artificial intelligence; Empirical risk minimization; Weighting; Generalization; Sample (material); Interpolation (computer graphics); Training set; Pattern recognition (psychology); Data mining; Image (mathematics); Mathematics","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":[0.004964975,0.001035753,0.0005629067,0.00115806,0.0005937387,0.002314105,0.002261164,0.002020697,0.006409367],"category_scores_gemma":[0.01183343,0.000871207,0.0007723523,0.0007713145,0.00193433,0.005130798,0.00325612,0.003740925,0.001216299],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001036242,"about_ca_system_score_gemma":0.0007463685,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00108275,"about_ca_topic_score_gemma":0.0009587657,"domain_scores_codex":[0.9979214,0.0007506655,0.0001201878,0.0004147987,0.0006777424,0.0001152909],"domain_scores_gemma":[0.9960266,0.002534021,0.0002244052,0.0006373241,0.0004779053,0.00009973761],"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":[0.00008064775,0.0000627562,0.001157031,0.000366963,0.00006799062,0.0001448685,0.0004713878,0.1696336,0.003683961,0.57121,0.00704327,0.2460776],"study_design_scores_gemma":[0.00001613991,0.00004579985,0.0003231199,0.0001385009,0.0000175753,0.0002204004,0.0000659611,0.7108114,0.005912028,0.2559821,0.02643728,0.00002960639],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00145516,0.0007340279,0.9942994,0.0004230094,0.00003443377,0.00003960405,0.00004776764,0.000231058,0.002735533],"genre_scores_gemma":[0.152703,0.002860866,0.8321553,0.0007619085,0.0002936901,0.0005403055,0.0003531693,0.0005912518,0.009740578],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006409367,"threshold_uncertainty_score":0.02625763,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4585232216924992,"score_gpt":0.4692555632666826,"score_spread":0.0107323415741834,"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."}}