{"id":"W2904990262","doi":"10.1609/aaai.v33i01.33014699","title":"Adversarial Dropout for Recurrent Neural Networks","year":2019,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"National Research Foundation of Korea; National Research Foundation","keywords":"Dropout (neural networks); Recurrent neural network; Computer science; MNIST database; Adversarial system; Generalization; Inference; Artificial intelligence; Machine learning; Artificial neural network; 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":[0.0006587557,0.0002786886,0.0003448301,0.0001138448,0.0002227593,0.0002532841,0.002771497,0.0001323015,0.00007588472],"category_scores_gemma":[0.0005758736,0.0002159488,0.0002243701,0.00053967,0.0001661914,0.0005416655,0.0006411093,0.0005056122,0.00005723833],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006705541,"about_ca_system_score_gemma":0.0000775971,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001745116,"about_ca_topic_score_gemma":0.000003661392,"domain_scores_codex":[0.9977558,0.00002789197,0.0005696166,0.0006606144,0.0004923039,0.000493728],"domain_scores_gemma":[0.9981507,0.0002447689,0.0005220218,0.0004098394,0.0005801279,0.00009254286],"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":[0.0002117614,0.00007920106,0.0005745001,0.0000394895,0.00001816452,1.880117e-7,0.0005703072,0.01523793,0.001979191,0.8855619,0.0001503017,0.09557702],"study_design_scores_gemma":[0.00007917265,0.0003834461,0.00007015093,0.000110145,0.00001365351,0.000002364154,0.0001935655,0.9440637,0.01400485,0.04059612,0.0002310461,0.000251737],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1106259,0.0000347563,0.8640958,0.005654097,0.007569303,0.002118868,0.000006628574,0.0002825695,0.00961207],"genre_scores_gemma":[0.9921725,0.000007693912,0.007013809,0.0001934209,0.0002730627,0.00003575386,9.741456e-7,0.00002011664,0.0002826346],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9288258,"threshold_uncertainty_score":0.8806137,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04608459895551688,"score_gpt":0.2972818511481127,"score_spread":0.2511972521925958,"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."}}