{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001519105,0.001340098,0.00102888,0.0007273247,0.0003576743,0.0009064288,0.001452557,0.001330337,0.001999348],"category_scores_gemma":[0.003912206,0.0003804534,0.001071266,0.0007467357,0.001121962,0.001645907,0.001614562,0.002753843,0.0004213304],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008107597,"about_ca_system_score_gemma":0.001091298,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001500966,"about_ca_topic_score_gemma":0.002354484,"domain_scores_codex":[0.9990776,0.0003414514,0.00003757188,0.0001177502,0.0003394141,0.0000862271],"domain_scores_gemma":[0.9987851,0.0006484946,0.0001528134,0.0001456109,0.0002086005,0.00005951188],"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":[0.0002115665,0.0001689834,0.0009892101,0.000243098,0.0001168134,0.0003740362,0.0001763734,0.6382097,0.0135009,0.1569246,0.01046801,0.1786168],"study_design_scores_gemma":[0.0000189003,0.00004386422,0.000103754,0.00002466132,0.00001149478,0.00005053751,0.00001111847,0.9697777,0.001911573,0.02672021,0.001319115,0.000007148457],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01259035,0.0004824758,0.9839903,0.000309297,0.00004050391,0.00003588187,0.00006349314,0.0002122156,0.002275544],"genre_scores_gemma":[0.3776569,0.001339617,0.6124099,0.0007237282,0.0002594839,0.0003139821,0.0006948833,0.0003739007,0.006227709],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.001999348,"threshold_uncertainty_score":0.008033872,"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."}}