{"id":"W2935694433","doi":"10.1007/978-3-030-18305-9_24","title":"Sparseout: Controlling Sparsity in Deep Networks","year":2019,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Dropout (neural networks); Computer science; Overfitting; Regularization (linguistics); Artificial neural network; Artificial intelligence; Deep neural networks; Contextual image classification; Source code; Image (mathematics); Machine learning; Property (philosophy); Code (set theory); Deep learning; Simple (philosophy)","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":[0.0008621998,0.0009710009,0.0007307185,0.0003779339,0.0002647541,0.0008985667,0.001334253,0.00109497,0.005598349],"category_scores_gemma":[0.003092378,0.000570729,0.0004153621,0.0005658026,0.0008969167,0.00175217,0.001606297,0.00245678,0.0009905569],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004736321,"about_ca_system_score_gemma":0.0004938963,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001545257,"about_ca_topic_score_gemma":0.002598919,"domain_scores_codex":[0.999747,0.00007375328,0.000009054636,0.0000569719,0.00008270142,0.00003051828],"domain_scores_gemma":[0.9991709,0.0005619156,0.00004820453,0.00009921072,0.00007379863,0.00004591802],"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":[0.0002233622,0.000125683,0.0003597961,0.0001913637,0.00006936009,0.0000736338,0.0000659291,0.5654289,0.01134412,0.08036343,0.02199965,0.3197548],"study_design_scores_gemma":[0.000009101171,0.00001953751,0.00003392536,0.000008103932,0.000005036733,0.000009738603,0.000003234336,0.9691303,0.001743233,0.02758847,0.001444879,0.000004393025],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005570363,0.0004668983,0.9895845,0.0002127774,0.0001208444,0.00001952891,0.0001101552,0.00123211,0.002682725],"genre_scores_gemma":[0.3735291,0.001940863,0.587787,0.0005692032,0.0004991635,0.000264213,0.001002794,0.002009811,0.03239787],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005598349,"threshold_uncertainty_score":0.01872832,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01319633625866369,"score_gpt":0.2332049262215444,"score_spread":0.2200085899628807,"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."}}