{"id":"W2780149736","doi":"10.1109/iccv.2017.305","title":"Centered Weight Normalization in Accelerating Training of Deep Neural Networks","year":2017,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":76,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Beihang University; National Natural Science Foundation of China; Canadian Institute for Advanced Research","keywords":"Computer science; Normalization (sociology); Artificial neural network; Convolutional neural network; Artificial intelligence; Scalability; Deep learning; Norm (philosophy); Deep neural networks; Perceptron; Curvature; Machine learning; Mathematical optimization; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001735271,0.001551278,0.0009788726,0.0008575909,0.0005387266,0.0007772875,0.001990463,0.001270446,0.003554537],"category_scores_gemma":[0.006758125,0.0008720858,0.0007831036,0.001229965,0.00111808,0.00254337,0.001817577,0.002772032,0.002586873],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009654927,"about_ca_system_score_gemma":0.00133044,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003068212,"about_ca_topic_score_gemma":0.004816346,"domain_scores_codex":[0.998938,0.000262538,0.00007234146,0.0002709993,0.0003484013,0.0001076687],"domain_scores_gemma":[0.998855,0.0003421593,0.000122697,0.0003122783,0.0003078653,0.00005995321],"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":[0.0002492869,0.0001605978,0.001413066,0.0002038476,0.0001024276,0.000157805,0.0002044973,0.45579,0.04390431,0.03480621,0.009988771,0.4530192],"study_design_scores_gemma":[0.00002559049,0.00005425935,0.0002449064,0.00002028351,0.00001509751,0.00006497177,0.00001667633,0.962825,0.01996671,0.01323656,0.003512179,0.00001783428],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01172912,0.0004140197,0.9820814,0.0001496093,0.0000831687,0.00004544686,0.00004189578,0.004336819,0.001118571],"genre_scores_gemma":[0.223427,0.0005075323,0.769455,0.0003138464,0.0001171876,0.0002579735,0.0003532606,0.00134185,0.00422645],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003554537,"threshold_uncertainty_score":0.01189107,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05577867744953627,"score_gpt":0.2934820380910469,"score_spread":0.2377033606415106,"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."}}