{"id":"W2136836265","doi":"","title":"Adaptive dropout for training deep neural networks","year":2013,"lang":"en","type":"article","venue":"neural information processing systems","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":280,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Dropout (neural networks); MNIST database; Computer science; Artificial intelligence; Artificial neural network; Feature (linguistics); Boltzmann machine; Deep belief network; Restricted Boltzmann machine; Stochastic gradient descent; Pattern recognition (psychology); Convolutional neural network; Machine learning; Gradient descent; Deep learning; Backpropagation","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0001742303,0.0002409663,0.0002513643,0.0001332559,0.0005361879,0.001099221,0.0007374412,0.0001033319,0.000003246236],"category_scores_gemma":[0.00004398571,0.0002144411,0.00007649128,0.0005951151,0.00005497367,0.008921999,0.0001023381,0.000213284,0.0000488699],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007187587,"about_ca_system_score_gemma":0.00003559096,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001756599,"about_ca_topic_score_gemma":0.000001609815,"domain_scores_codex":[0.9981577,0.00004346713,0.0007097769,0.000276028,0.0002867118,0.0005263464],"domain_scores_gemma":[0.998305,0.0001530632,0.0005425934,0.0003658377,0.0004783446,0.0001551675],"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":[0.0000064519,0.000009153422,0.00002730403,0.00006638201,0.000006723537,2.754708e-7,0.001690027,0.4083112,0.00003837342,0.01029106,0.000878065,0.578675],"study_design_scores_gemma":[0.000289654,0.00006830336,0.00008848021,0.00002963092,0.000004844844,0.00004508556,0.000522561,0.9957029,0.00001889275,0.0006666981,0.00231625,0.000246656],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001684411,0.0002447148,0.9939305,0.0006971702,0.0006547029,0.00141096,0.000002594391,0.0006021471,0.0007728419],"genre_scores_gemma":[0.9786201,0.000002413998,0.01889288,0.0009002767,0.0002740725,0.001178846,0.0000297021,0.00001675906,0.00008499255],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9769356,"threshold_uncertainty_score":0.9999377,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03198876176642353,"score_gpt":0.2623541483614051,"score_spread":0.2303653865949816,"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."}}