{"id":"W2952316226","doi":"10.48550/arxiv.1902.08673","title":"Ising-Dropout: A Regularization Method for Training and Compression of Deep Neural Networks","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"MNIST database; Overfitting; Computer science; Initialization; Artificial intelligence; Regularization (linguistics); Dropout (neural networks); Inference; Machine learning; Artificial neural network; Deep neural networks; Deep learning; Pattern recognition (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":[],"consensus_categories":[],"category_scores_codex":[0.0004207507,0.0001732285,0.0002917407,0.0001633202,0.0001143716,0.00008247,0.0006642883,0.0002151619,0.00000274343],"category_scores_gemma":[0.00006505942,0.0001885835,0.00008905199,0.0002362723,0.0000462015,0.0002494097,0.0007156482,0.0003132287,7.623104e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000342988,"about_ca_system_score_gemma":0.00003760588,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004294273,"about_ca_topic_score_gemma":0.000006485703,"domain_scores_codex":[0.9986202,0.0002303521,0.0001872061,0.0007275571,0.00005757602,0.0001770841],"domain_scores_gemma":[0.9984103,0.0002589559,0.0004148783,0.0007275376,0.0001209117,0.00006738091],"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":[0.00002763621,0.00002198808,0.001321575,0.0001103453,0.00002495651,0.000002422212,0.0003823546,0.8706715,0.00008940935,0.0900633,0.0000191714,0.03726538],"study_design_scores_gemma":[0.0003847423,0.00005170912,0.001119159,0.00006700942,0.00004558274,0.000002579063,0.00005724959,0.9888982,0.00002566808,0.009028403,0.000137164,0.0001826044],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007661327,0.00007896585,0.9911515,0.0001043568,0.000314588,0.0003042181,0.000008287212,0.00009101567,0.0002857659],"genre_scores_gemma":[0.9428616,0.00002767336,0.0566921,0.00003601043,0.0000433915,7.994695e-7,0.0001135674,0.00001196224,0.0002129021],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9352003,"threshold_uncertainty_score":0.7690212,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07685834504908302,"score_gpt":0.2346372853127585,"score_spread":0.1577789402636754,"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."}}