{"id":"W4288598872","doi":"10.48550/arxiv.1902.08673","title":"Ising-Dropout: A Regularization Method for Training and Compression of\\n Deep Neural Networks","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"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; Artificial 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001828904,0.00110992,0.000824677,0.0008574876,0.0005954772,0.0007553146,0.00216804,0.001604373,0.002346421],"category_scores_gemma":[0.004758471,0.0004850159,0.0009106611,0.00105213,0.001110352,0.001604318,0.001422464,0.003198729,0.0006667026],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001460283,"about_ca_system_score_gemma":0.001469395,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005580915,"about_ca_topic_score_gemma":0.008077668,"domain_scores_codex":[0.9994391,0.0001480739,0.00005139492,0.00008293228,0.0002178857,0.00006060111],"domain_scores_gemma":[0.9990681,0.000370082,0.0001044304,0.0002197047,0.0001826131,0.00005516177],"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":[0.0004186558,0.0002547818,0.001421615,0.0002178616,0.000159702,0.0002738372,0.0002138726,0.6141262,0.01716513,0.04608052,0.009675235,0.3099926],"study_design_scores_gemma":[0.000007830922,0.0000221791,0.00009611731,0.000009589404,0.000006643755,0.00001952181,0.000004332411,0.9914346,0.003491526,0.004066486,0.0008350706,0.000006015243],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01463452,0.0004243744,0.9808436,0.0003432339,0.0001118056,0.00007701841,0.0001403949,0.001847087,0.001577913],"genre_scores_gemma":[0.4393098,0.001068122,0.5447001,0.000591853,0.0002763536,0.0005025792,0.001279344,0.0008338537,0.01143797],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005580915,"threshold_uncertainty_score":0.01109684,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0765926445852397,"score_gpt":0.2345336015730993,"score_spread":0.1579409569878596,"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."}}