{"id":"W4395673742","doi":"10.3390/app14093669","title":"Pruning Deep Neural Network Models via Minimax Concave Penalty Regression","year":2024,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Hubei Provincial Department of Education; National Social Science Fund of China; National Office for Philosophy and Social Sciences; National Natural Science Foundation of China; Canadian Institute for Advanced Research","keywords":"Minimax; Artificial neural network; Computer science; Pruning; Regression; Deep neural networks; Artificial intelligence; Mathematics; Mathematical optimization; Statistics; Biology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005026682,0.0001395071,0.0001242791,0.00009625989,0.0006790491,0.0004965915,0.000958467,0.00005958402,0.00001982459],"category_scores_gemma":[0.000002772826,0.0001041924,0.00005835439,0.001290126,0.0002261874,0.0005593064,0.0002801934,0.0001681055,0.00005195235],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002891252,"about_ca_system_score_gemma":0.00005635428,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001322272,"about_ca_topic_score_gemma":0.00000509048,"domain_scores_codex":[0.9984709,0.00002271679,0.0002144692,0.0006108494,0.0003309574,0.000350097],"domain_scores_gemma":[0.9993851,0.0001115527,0.00006676302,0.0003168718,0.00002756081,0.00009216113],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00000188062,0.00001368197,0.00001745162,0.00001044006,0.000005291755,0.000005251674,0.0004587438,0.01779418,0.003664464,0.7870127,0.002115408,0.1889005],"study_design_scores_gemma":[0.00002844474,0.00003876203,0.00003788625,0.00001710972,0.000003427228,0.00001851729,0.00004717514,0.8891534,0.002684801,0.1048897,0.002936482,0.0001442724],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005798642,0.0004927145,0.9658212,0.0008276161,0.0002395822,0.000228995,5.054729e-7,0.0007952555,0.02579548],"genre_scores_gemma":[0.9093413,0.00001736013,0.08990769,0.0003365865,0.000136217,0.00009947924,8.940792e-7,0.000006646223,0.0001537912],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9035427,"threshold_uncertainty_score":0.5222765,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0291427606070673,"score_gpt":0.2788633953610094,"score_spread":0.2497206347539421,"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."}}