{"id":"W2916313152","doi":"10.1109/icassp.2019.8682914","title":"Ising-dropout: A Regularization Method for Training and Compression of Deep Neural Networks","year":2019,"lang":"en","type":"article","venue":"","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"MNIST database; Overfitting; Computer science; Artificial intelligence; Dropout (neural networks); Initialization; Regularization (linguistics); Artificial neural network; Machine learning; Inference; Deep learning; Deep neural networks; 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":[0.0001436061,0.00006411154,0.0001232568,0.00002692001,0.00006486115,0.00004828653,0.0001913796,0.00003772855,0.000005762238],"category_scores_gemma":[0.00000462378,0.00005153329,0.00003159065,0.0001630674,0.00001396174,0.0001710381,0.00008607882,0.00004557556,3.878225e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003313952,"about_ca_system_score_gemma":0.000003981604,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004406008,"about_ca_topic_score_gemma":0.000002029716,"domain_scores_codex":[0.9994159,0.00002862677,0.0001481027,0.0002139608,0.00006843969,0.000125007],"domain_scores_gemma":[0.9994545,0.0001671049,0.00008060483,0.0002167488,0.00004317153,0.00003786602],"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":[0.000007386703,0.00002318393,0.0003164807,0.00001882202,0.000007745252,1.502002e-7,0.0003278952,0.07956523,0.006511782,0.2685863,0.0001361447,0.6444988],"study_design_scores_gemma":[0.0002070563,0.0000470721,0.0002584575,0.000008987784,0.000003642997,0.000004152375,0.00002122639,0.9931853,0.0005840032,0.005277002,0.0003391079,0.00006403369],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005253547,0.00006374733,0.9933361,0.0004874243,0.00009703226,0.0002825978,4.256966e-7,0.00004699138,0.0004321017],"genre_scores_gemma":[0.7013347,0.000002582647,0.2983099,0.000178665,0.00003080916,0.000009547472,0.000003208586,0.000004294885,0.0001263119],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9136201,"threshold_uncertainty_score":0.2101467,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02080000613618969,"score_gpt":0.2862139738270688,"score_spread":0.265413967690879,"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."}}