{"id":"W4389339766","doi":"10.1137/22m1542313","title":"Deep Neural Networks Pruning via the Structured Perspective Regularization","year":2023,"lang":"en","type":"article","venue":"SIAM Journal on Mathematics of Data Science","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Huawei Technologies (Canada); Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Regularization (linguistics); Artificial neural network; Artificial intelligence; Deep neural networks; Pruning; Perspective (graphical); Computer science; Mathematics; Machine learning; Biology; Botany","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":[0.00149896,0.0001079511,0.0001315806,0.0001465449,0.0007591978,0.0004257637,0.004676465,0.0000267578,0.00000530921],"category_scores_gemma":[0.0001998897,0.00006700328,0.00003677979,0.002413564,0.0003045058,0.00156052,0.0008923975,0.0003014089,0.000007561307],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003677759,"about_ca_system_score_gemma":0.00006224334,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001384998,"about_ca_topic_score_gemma":0.000001910043,"domain_scores_codex":[0.9983143,0.00004378278,0.0003131963,0.0003228934,0.0007055094,0.0003002781],"domain_scores_gemma":[0.9977157,0.0002408946,0.0003744515,0.001324628,0.0002459838,0.00009838383],"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":[0.000003168245,0.00006139744,0.00002052675,0.00001067902,0.00001577117,0.000009770039,0.001559941,0.2474325,0.003354617,0.705866,0.0008295047,0.0408361],"study_design_scores_gemma":[0.00006184166,0.00003576931,0.0003117881,0.00002184918,0.000005636186,0.00007506832,0.000200187,0.9226255,0.0001472366,0.0764001,0.00004401491,0.00007101388],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003923722,0.00005126288,0.9921346,0.003048464,0.0002727038,0.0001730306,0.000002973517,0.00005737951,0.0003359115],"genre_scores_gemma":[0.9221468,0.00005474755,0.07738983,0.0001709295,0.000178213,0.000003430174,0.000005324692,0.000009760011,0.00004099295],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9182231,"threshold_uncertainty_score":0.8690114,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03930905499830477,"score_gpt":0.3110639967382346,"score_spread":0.2717549417399298,"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."}}