{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001416671,0.0006500835,0.0008075365,0.000274607,0.0006238185,0.0007719395,0.004161227,0.000516629,0.00007175614],"category_scores_gemma":[0.002532183,0.0005472933,0.0003359277,0.0004561985,0.0006807263,0.0004765356,0.004103677,0.001593942,0.00003112371],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001135852,"about_ca_system_score_gemma":0.0003570387,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009281447,"about_ca_topic_score_gemma":0.000008231287,"domain_scores_codex":[0.9959921,0.00008243974,0.000983534,0.001474446,0.0007906723,0.0006768731],"domain_scores_gemma":[0.9963344,0.0004100644,0.0009732538,0.0006431207,0.001458562,0.0001805727],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006764788,0.0002535116,0.001524405,0.001022555,0.0002041802,0.00000180143,0.01098524,0.006700512,0.01895647,0.8326641,0.0004806396,0.12653],"study_design_scores_gemma":[0.0001216963,0.0003399148,0.00005524789,0.0007064181,0.00006642601,0.00000390048,0.0005952587,0.7787946,0.04704812,0.1714558,0.0002362722,0.0005763042],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2151357,0.0001007511,0.760958,0.006751853,0.004996997,0.003128703,0.00003376331,0.0006004414,0.008293852],"genre_scores_gemma":[0.9655205,0.00006661731,0.03307552,0.0001591867,0.0006624339,0.0001138813,0.000005397573,0.00005628047,0.0003401967],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7720941,"threshold_uncertainty_score":0.9996979,"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."}}