{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000237462,0.00009219494,0.0001028189,0.00006905394,0.0002669354,0.0002138782,0.001392782,0.00003503475,0.00001683034],"category_scores_gemma":[0.00002434089,0.0000879747,0.00003141638,0.000723833,0.00009279809,0.0009710767,0.0001919886,0.00009723637,0.00004178727],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006506857,"about_ca_system_score_gemma":0.00002779922,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003358304,"about_ca_topic_score_gemma":0.000009004946,"domain_scores_codex":[0.9990693,0.00006222772,0.0001436064,0.0003331554,0.0001221461,0.0002696102],"domain_scores_gemma":[0.9990671,0.0002377886,0.00007529063,0.0004994437,0.00004165773,0.00007867635],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000007842975,0.00004129209,0.0002687345,0.00001056713,0.00003340149,0.00001076424,0.002849526,0.001233202,0.01945725,0.5851484,0.01072408,0.3802149],"study_design_scores_gemma":[0.0003729599,0.00008175681,0.0005938952,0.00003357376,0.00001115179,0.00003912205,0.0001051415,0.1969499,0.07269453,0.6975534,0.03103544,0.0005291122],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001369641,0.00001993551,0.9879366,0.0007901763,0.000709158,0.0001049047,4.211376e-7,0.0002616477,0.008807481],"genre_scores_gemma":[0.6332228,0.000004955893,0.3657032,0.000657165,0.000300886,0.00001857181,2.762094e-7,0.000008361778,0.00008379371],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6318532,"threshold_uncertainty_score":0.3587504,"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."}}