{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001888673,0.0009689697,0.0007894153,0.0008552534,0.0005335741,0.0006768239,0.001758816,0.001384952,0.001685031],"category_scores_gemma":[0.005088385,0.0004392034,0.0008845098,0.001136576,0.0009128133,0.001501989,0.001204301,0.002785456,0.0005142081],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001131155,"about_ca_system_score_gemma":0.0011379,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00324019,"about_ca_topic_score_gemma":0.004176126,"domain_scores_codex":[0.9993686,0.0001723125,0.00006556594,0.00008829704,0.0002465401,0.00005875062],"domain_scores_gemma":[0.9989979,0.0003979273,0.0001168038,0.0002428274,0.0001986767,0.00004597456],"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":[0.0003890216,0.0002474495,0.001649134,0.0002560198,0.0001820182,0.000289293,0.0002247596,0.5781911,0.02538889,0.04679153,0.007505059,0.3388857],"study_design_scores_gemma":[0.00001099041,0.00003053341,0.0001436254,0.00001163155,0.000009775804,0.00002897381,0.000004842651,0.9866287,0.006081666,0.00595023,0.001090107,0.000008931804],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01209193,0.0003810959,0.9844956,0.0002642515,0.00009158513,0.00006907666,0.0001133065,0.00147556,0.001017557],"genre_scores_gemma":[0.3909961,0.001009292,0.5984585,0.0004092299,0.0002202066,0.0004939281,0.0009056251,0.0006872652,0.006819881],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00324019,"threshold_uncertainty_score":0.009988427,"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."}}