{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003547559,0.001880651,0.001535537,0.0009971253,0.0007742886,0.001579799,0.003284661,0.002438632,0.002387439],"category_scores_gemma":[0.007702904,0.001109407,0.001338793,0.0009267264,0.002225545,0.003019148,0.005379437,0.004540794,0.001199007],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00111927,"about_ca_system_score_gemma":0.001220108,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001494465,"about_ca_topic_score_gemma":0.002296479,"domain_scores_codex":[0.9984075,0.0007069752,0.00007935652,0.0003507232,0.0003333669,0.0001219797],"domain_scores_gemma":[0.9976706,0.001001208,0.0002285649,0.000690654,0.0002625796,0.0001463773],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0005145665,0.0002950891,0.00359957,0.0003674467,0.0003000371,0.0002478311,0.0004390044,0.6598876,0.01350846,0.0537295,0.0118996,0.2552112],"study_design_scores_gemma":[0.00001585377,0.00007355284,0.0001104186,0.00001597844,0.00001239727,0.00003284136,0.00001318764,0.9857668,0.002395124,0.01005105,0.001500506,0.00001229848],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02621372,0.0006348087,0.968236,0.0004158118,0.00006158227,0.0001223885,0.00014884,0.002734759,0.001431991],"genre_scores_gemma":[0.4985226,0.0004941036,0.4901173,0.000931118,0.0001628358,0.0006859364,0.001157534,0.0009908316,0.006937818],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003547559,"threshold_uncertainty_score":0.01876152,"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."}}