{"id":"W2900763636","doi":"10.1109/cvpr.2019.00932","title":"Structured Pruning of Neural Networks With Budget-Aware Regularization","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke","funders":"Mitacs; Compute Canada","keywords":"Computer science; Pruning; Regularization (linguistics); Artificial neural network; Inference; Deep neural networks; Artificial intelligence; Residual; Machine learning; Feature (linguistics); Dropout (neural networks); Algorithm","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.00007431819,0.0002934762,0.0003604583,0.0001006529,0.00007690801,0.00009328197,0.001406431,0.0002341983,0.0000094317],"category_scores_gemma":[0.000006135811,0.0002399266,0.00007082726,0.0004937802,0.00006610697,0.0002583347,0.001341391,0.0005534909,0.000002108903],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004298057,"about_ca_system_score_gemma":0.00008250831,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007505397,"about_ca_topic_score_gemma":0.00001244353,"domain_scores_codex":[0.9982231,0.00006037135,0.0003606171,0.0007618297,0.0003128411,0.0002812477],"domain_scores_gemma":[0.9973995,0.00008475504,0.0005099203,0.00170075,0.0002326825,0.00007236071],"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":[0.000006692927,0.000009449062,0.0005727276,0.00003492755,0.00001933399,0.000001262216,0.00005189101,0.9710021,0.00005876502,0.02114625,0.0001451939,0.006951406],"study_design_scores_gemma":[0.0001631052,0.00004119969,0.00194375,0.00006284301,0.00001450586,0.000009634809,0.000005801652,0.9897448,0.0005512856,0.007105285,0.00008283631,0.0002749189],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002601312,0.00009345491,0.9948291,0.0004520788,0.0003707565,0.0007847971,0.000006088164,0.0002987898,0.0005636224],"genre_scores_gemma":[0.8294525,0.00001617,0.169543,0.0001599848,0.0001033193,0.00004528442,0.0001085641,0.00002964727,0.0005416207],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8268511,"threshold_uncertainty_score":0.9783921,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01120915455717737,"score_gpt":0.2397131926062216,"score_spread":0.2285040380490442,"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."}}