{"id":"W2891021639","doi":"10.1609/aaai.v33i01.33013714","title":"MixUp as Locally Linear Out-of-Manifold Regularization","year":2019,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":265,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa; National Research Council Canada","funders":"National Key Research and Development Program of China; Beijing Advanced Innovation Center for Big Data and Brain Computing; National Natural Science Foundation of China","keywords":"Computer science; Regularization (linguistics); Manifold (fluid mechanics); Artificial neural network; Benchmark (surveying); Artificial intelligence; Machine learning; Mixing (physics); Nonlinear dimensionality reduction; Algorithm; Dimensionality 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":[],"consensus_categories":[],"category_scores_codex":[0.0005541189,0.0001638984,0.0002206881,0.0001192705,0.00008521361,0.0001265951,0.00199932,0.00009675505,0.00009262513],"category_scores_gemma":[0.0005136003,0.0001259823,0.00008714118,0.0005025837,0.00009998667,0.0004277253,0.0003482146,0.0002511619,0.0004791806],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002569992,"about_ca_system_score_gemma":0.0001122369,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003899543,"about_ca_topic_score_gemma":0.000004469645,"domain_scores_codex":[0.9982797,0.00002410815,0.0005129222,0.0004562135,0.0005176628,0.0002094174],"domain_scores_gemma":[0.9981741,0.00007522299,0.0005461858,0.0004846951,0.000661285,0.00005852024],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003261459,0.00006171255,0.0005906293,0.00004576101,0.000007551959,8.619432e-8,0.0006860977,0.00007808337,0.078852,0.8918898,0.00005471327,0.02770102],"study_design_scores_gemma":[0.00004123158,0.0003605091,0.0005947843,0.0002782055,0.00001172339,0.000002241122,0.0002725825,0.2510752,0.6250774,0.1211256,0.000931567,0.0002288899],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3311834,0.0000512027,0.515138,0.01792201,0.002716268,0.001697727,0.00001464085,0.0004031312,0.1308737],"genre_scores_gemma":[0.9935583,0.00002005828,0.004504894,0.0001482085,0.00004885949,0.000007322843,0.000002548161,0.00001009711,0.001699744],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7707641,"threshold_uncertainty_score":0.6159057,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05000555547855106,"score_gpt":0.29572975316366,"score_spread":0.2457241976851089,"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."}}