{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001822283,0.0009660784,0.000772575,0.0008267668,0.0005403887,0.0006181599,0.001682077,0.001254709,0.001762277],"category_scores_gemma":[0.004690632,0.0004020394,0.0008894082,0.001109459,0.0008280468,0.00144387,0.001119391,0.002536091,0.0004978926],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001060868,"about_ca_system_score_gemma":0.001183607,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003711796,"about_ca_topic_score_gemma":0.004835306,"domain_scores_codex":[0.9993796,0.0001550747,0.00006855958,0.00008505761,0.0002514887,0.00006016643],"domain_scores_gemma":[0.9990841,0.0003442283,0.0001121661,0.000216853,0.0002001184,0.00004252878],"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":[0.0004212112,0.0002677935,0.001838764,0.0002692714,0.0001845865,0.0003104875,0.0002422744,0.5404518,0.0284661,0.03789325,0.008000402,0.3816541],"study_design_scores_gemma":[0.00001191372,0.00003577088,0.0001827936,0.00001240564,0.00001120609,0.00003315558,0.000006007031,0.9861373,0.007836185,0.004448159,0.001274859,0.00001033997],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01340358,0.0004009053,0.9829525,0.0002461416,0.00009606584,0.00007802311,0.0001291246,0.001635903,0.001057714],"genre_scores_gemma":[0.384876,0.0009716377,0.6045907,0.0003875992,0.0001849946,0.0005096071,0.0009994261,0.0006702686,0.006809838],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003711796,"threshold_uncertainty_score":0.009637237,"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."}}