{"id":"W3087886149","doi":"10.1109/access.2020.3040256","title":"Pruning Convolutional Filters Using Batch Bridgeout","year":2020,"lang":"en","type":"preprint","venue":"IEEE Access","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada; Canada First Research Excellence Fund","keywords":"Computer science; Regularization (linguistics); Inference; Convolutional neural network; Pruning; Residual neural network; Artificial intelligence; Machine learning; Generalization; Overfitting; Artificial neural network; FLOPS; Pattern recognition (psychology); Mathematics; Parallel computing","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00009162498,0.0002946743,0.0003069956,0.00009358393,0.0002241032,0.0005394456,0.003739916,0.0001540711,0.00001360233],"category_scores_gemma":[0.0000299978,0.0003332838,0.0001242776,0.0004901073,0.00008086101,0.0007242849,0.003229154,0.0007261909,0.00004966763],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001580038,"about_ca_system_score_gemma":0.0002706546,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007540497,"about_ca_topic_score_gemma":0.000005697788,"domain_scores_codex":[0.9978077,0.0000633037,0.0003667058,0.001002289,0.0003859655,0.0003739899],"domain_scores_gemma":[0.9981939,0.0001456096,0.0003455849,0.001004247,0.0001376909,0.000172942],"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":[0.00001270925,0.00007013772,0.001406071,0.0001802962,0.000113398,0.0000757922,0.0003741211,0.9441866,0.005555259,0.01472693,0.01696661,0.01633202],"study_design_scores_gemma":[0.0001586298,0.000008561213,0.001479913,0.0001185053,0.0000207601,0.0000237586,0.000002568872,0.9604442,0.002684277,0.03101701,0.0035204,0.0005214005],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0177949,0.0001189036,0.976566,0.00254044,0.001662992,0.0004442539,0.00003105997,0.0004171081,0.0004243648],"genre_scores_gemma":[0.8773687,0.00003910931,0.1198103,0.001640187,0.0008800441,0.0001103848,0.00004031795,0.000037597,0.00007331795],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8595738,"threshold_uncertainty_score":0.9999119,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.144974455153314,"score_gpt":0.3717675072465475,"score_spread":0.2267930520932335,"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."}}