{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001584168,0.001189269,0.001111337,0.000740228,0.0005604799,0.0006812883,0.001844297,0.00165395,0.002910797],"category_scores_gemma":[0.004533208,0.0006113301,0.0009900532,0.0005059299,0.0008932027,0.001543446,0.0011503,0.001823383,0.0009415926],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007994788,"about_ca_system_score_gemma":0.001292097,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005834463,"about_ca_topic_score_gemma":0.01138744,"domain_scores_codex":[0.9994814,0.00008801467,0.00003317674,0.0001636162,0.0001563144,0.00007757836],"domain_scores_gemma":[0.9985897,0.0005839057,0.0001338385,0.0003018659,0.0003106668,0.0000799723],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000723815,0.0004126479,0.003227288,0.0001745624,0.0002113261,0.0004479806,0.000271078,0.446894,0.0480788,0.01119812,0.01357832,0.4747821],"study_design_scores_gemma":[0.0000198524,0.00006412352,0.000286755,0.000009080063,0.00001752536,0.00006215443,0.00001155053,0.9868135,0.008808874,0.003042489,0.0008553138,0.000008643311],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06342478,0.0004959301,0.929337,0.000202791,0.0001028053,0.00008371145,0.0001435352,0.004498975,0.001710484],"genre_scores_gemma":[0.612807,0.0002921024,0.3740048,0.0006383305,0.00009016169,0.0002542479,0.001271404,0.0007935693,0.009848282],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005834463,"threshold_uncertainty_score":0.01160097,"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."}}