{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001774322,0.0003607483,0.0006635516,0.0002442951,0.0001217146,0.00007617447,0.003040005,0.0004285033,0.00001536862],"category_scores_gemma":[0.0004863889,0.0004198934,0.0003171933,0.0006567367,0.0001223899,0.0003076781,0.003409306,0.0008636883,0.000006339558],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001371828,"about_ca_system_score_gemma":0.000143538,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005509685,"about_ca_topic_score_gemma":0.00006752316,"domain_scores_codex":[0.9968387,0.001129391,0.000327132,0.001181129,0.00007764282,0.0004460342],"domain_scores_gemma":[0.9955459,0.001670988,0.0006412753,0.001607395,0.000413352,0.0001211396],"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":[0.00004856085,0.00002814685,0.01452903,0.00008148091,0.0000871757,0.00001017281,0.00007931787,0.9549728,0.000003110458,0.02200009,0.00003061088,0.008129469],"study_design_scores_gemma":[0.0004873964,0.00006279674,0.00568577,0.00003266328,0.00006178531,0.000001141911,0.00001332577,0.9876853,0.00001353313,0.005509179,0.00005162894,0.0003955339],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007213714,0.0001639002,0.9892857,0.00003036732,0.002257405,0.0005270501,0.000009747338,0.0001517376,0.0003603522],"genre_scores_gemma":[0.9000487,0.00002579367,0.09936794,0.00004176432,0.00007463362,0.000001052263,0.00004003926,0.0000314939,0.0003685879],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.892835,"threshold_uncertainty_score":0.9998253,"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."}}