{"id":"W2734426634","doi":"10.1609/aaai.v32i1.11634","title":"Adversarial Dropout for Supervised and Semi-Supervised Learning","year":2018,"lang":"en","type":"preprint","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"National Research Foundation of Korea; National Research Foundation","keywords":"Generality; Dropout (neural networks); MNIST database; Adversarial system; Computer science; Machine learning; Artificial intelligence; Artificial neural network; Generalization; Set (abstract data type); Deep neural networks; Supervised learning; Mathematics; Psychology","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":[0.005549772,0.001430365,0.00139101,0.0008272806,0.0005790681,0.001102823,0.002071774,0.001790833,0.001758113],"category_scores_gemma":[0.01342946,0.0005861729,0.001084773,0.0007858415,0.002858663,0.002353231,0.002600778,0.00397576,0.0004160445],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001697499,"about_ca_system_score_gemma":0.001121354,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001373952,"about_ca_topic_score_gemma":0.001354594,"domain_scores_codex":[0.9969825,0.0014008,0.0001582321,0.0006131011,0.000682472,0.0001629623],"domain_scores_gemma":[0.992633,0.004863449,0.0006441826,0.001182359,0.000493239,0.000183721],"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":[0.0001533171,0.00008384507,0.0008038949,0.0002330823,0.0001336044,0.000148863,0.0001381271,0.8105924,0.003594929,0.1153806,0.003320988,0.06541628],"study_design_scores_gemma":[0.000006046077,0.00002313324,0.00009636726,0.00001116941,0.000005236157,0.0000207923,0.000003402394,0.9668929,0.0009658983,0.03135328,0.0006149192,0.000006881591],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005576366,0.0004224332,0.9920568,0.0002967524,0.00004154814,0.00003832262,0.0000602988,0.0003518313,0.001155637],"genre_scores_gemma":[0.7004999,0.001234074,0.2915252,0.0005711348,0.0003466936,0.0004270204,0.00058483,0.0002775936,0.004533532],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005549772,"threshold_uncertainty_score":0.02935034,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06696556916244889,"score_gpt":0.3084728003732138,"score_spread":0.2415072312107649,"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."}}