{"id":"W2963080758","doi":"10.1609/aaai.v32i1.11634","title":"Adversarial Dropout for Supervised and Semi-Supervised Learning","year":2018,"lang":"en","type":"article","venue":"","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":162,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"National Research Foundation of Korea; National Research Foundation","keywords":"Adversarial system; Regularization (linguistics); Generality; MNIST database; Computer science; Machine learning; Artificial intelligence; Artificial neural network; Dropout (neural networks); Generalization; Supervised learning; Mathematics","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":[0.0005809365,0.0002215719,0.0002500569,0.0001244573,0.0005755547,0.0002367495,0.0007166299,0.0001249611,0.0001507752],"category_scores_gemma":[0.0005055921,0.0002048981,0.00008202986,0.0002846916,0.0001581457,0.0007107569,0.0005469187,0.0002567263,0.00005986715],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003898998,"about_ca_system_score_gemma":0.00007881903,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008264121,"about_ca_topic_score_gemma":0.0000136541,"domain_scores_codex":[0.9982501,0.000126243,0.000259418,0.0006339073,0.0002597974,0.0004705841],"domain_scores_gemma":[0.9988127,0.0003596324,0.00007624629,0.0004169088,0.0001803907,0.0001541704],"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":[0.0006585937,0.000245053,0.04233064,0.0002449877,0.0003381484,0.00004260295,0.02040809,0.008538458,0.02049143,0.3642837,0.00912749,0.5332907],"study_design_scores_gemma":[0.001841748,0.0003346053,0.0003661113,0.0000155506,0.00001475493,0.00001106695,0.0002041457,0.9749968,0.001006594,0.001906789,0.01898514,0.0003167064],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02375646,0.0000282602,0.9662988,0.001069746,0.0008204485,0.0003134899,8.98729e-7,0.0004900619,0.00722188],"genre_scores_gemma":[0.7343767,0.000004869103,0.2626332,0.0004961165,0.0007633004,0.00001873573,0.000005002214,0.00002598678,0.001676076],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9664583,"threshold_uncertainty_score":0.8355502,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01501898056914173,"score_gpt":0.2662634749676445,"score_spread":0.2512444943985028,"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."}}