{"id":"W2943008967","doi":"10.48550/arxiv.1904.13310","title":"Survey of Dropout Methods for Deep Neural Networks","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Dropout (neural networks); Artificial neural network; Computer science; Artificial intelligence; Inference; Regularization (linguistics); Convolutional neural network; Machine learning; Deep neural networks; Deep learning","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":[0.004356591,0.001777797,0.002230296,0.001420317,0.0005773574,0.00183359,0.002775016,0.001981816,0.004206546],"category_scores_gemma":[0.009062241,0.0009871019,0.00155031,0.001828452,0.001320273,0.003064763,0.002776826,0.003934439,0.001860771],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001815746,"about_ca_system_score_gemma":0.001741115,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002765696,"about_ca_topic_score_gemma":0.002204571,"domain_scores_codex":[0.9980773,0.0004952197,0.0001667452,0.0002712868,0.0008894042,0.0001001019],"domain_scores_gemma":[0.9977046,0.001319351,0.0001561876,0.0002952412,0.0004513625,0.00007333705],"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":[0.0002732877,0.0001368469,0.001090209,0.00204719,0.0003425606,0.0001710677,0.0001629475,0.1587852,0.002827739,0.1432818,0.02385678,0.6670243],"study_design_scores_gemma":[0.00005805747,0.0001745606,0.0008336324,0.0008190747,0.0001314088,0.0003027324,0.00003924246,0.7604631,0.006174972,0.1356641,0.09527036,0.00006867787],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002790048,0.06727277,0.9198678,0.001605218,0.0004567641,0.00009039117,0.0003295919,0.0009016041,0.006685739],"genre_scores_gemma":[0.2126978,0.2054097,0.5381707,0.002854942,0.003852626,0.0007630278,0.002895611,0.001817198,0.03153845],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004356591,"threshold_uncertainty_score":0.02304012,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1004422739729258,"score_gpt":0.2735235226681901,"score_spread":0.1730812486952644,"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."}}