{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.001959207,0.0007352181,0.001020669,0.001137908,0.0002503979,0.0005812648,0.005098972,0.0006047712,0.00003239136],"category_scores_gemma":[0.0002498889,0.0007350776,0.0001873013,0.0009336043,0.000534282,0.0008570041,0.002641221,0.002555911,0.00008329092],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006208222,"about_ca_system_score_gemma":0.0005797577,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006851855,"about_ca_topic_score_gemma":0.0003463035,"domain_scores_codex":[0.9946364,0.0001093066,0.000775687,0.002180051,0.00112769,0.001170841],"domain_scores_gemma":[0.9961204,0.001174662,0.000496498,0.001843809,0.0001776226,0.0001870117],"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":[0.000009787554,0.00001317698,0.000815441,0.00001471007,0.000006972362,0.000138509,0.0003073726,0.797626,0.000004664783,0.01657308,0.000002245632,0.1844881],"study_design_scores_gemma":[0.0006351878,0.00007817276,0.0004855534,0.000365859,0.000007415879,0.00003774009,1.720171e-7,0.9545808,0.00001641715,0.04259188,0.0004627927,0.0007380091],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00008340842,0.0006723984,0.9900035,0.0004415485,0.004017334,0.0005893362,0.000001067682,0.0001878325,0.004003626],"genre_scores_gemma":[0.623659,0.00006176027,0.3731729,0.001700747,0.0009749698,0.000006182566,0.000006184577,0.0000714171,0.0003468326],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6235756,"threshold_uncertainty_score":0.9997452,"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."}}