{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00517153,0.001443163,0.00137609,0.0007852673,0.0005726871,0.0009905711,0.002042722,0.001621186,0.001545513],"category_scores_gemma":[0.01159116,0.0005640553,0.001052174,0.0007646843,0.002662536,0.002315409,0.002369597,0.003689343,0.0003635552],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001599339,"about_ca_system_score_gemma":0.001090352,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001461843,"about_ca_topic_score_gemma":0.001468455,"domain_scores_codex":[0.9973551,0.001198896,0.000151848,0.000542914,0.0006039276,0.0001473407],"domain_scores_gemma":[0.9936387,0.004137061,0.0005776372,0.001017475,0.0004617415,0.0001673799],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001491473,0.00008229059,0.0007694911,0.0002243821,0.0001230008,0.0001394318,0.0001267958,0.8314747,0.004043713,0.0925639,0.002828618,0.06747454],"study_design_scores_gemma":[0.000005333024,0.00002417324,0.00009067476,0.000009967269,0.000005370665,0.00001993983,0.000003147997,0.9754954,0.001052694,0.02273793,0.0005486041,0.00000680718],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005737717,0.0004280373,0.9921251,0.0002449022,0.00003929208,0.00003608874,0.00005312245,0.0003417669,0.0009940166],"genre_scores_gemma":[0.6982292,0.001257633,0.2946459,0.000500353,0.0003000113,0.0003880266,0.0005143444,0.000242643,0.003921891],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00517153,"threshold_uncertainty_score":0.02734995,"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."}}