{"id":"W4413407902","doi":"10.1016/j.neucom.2025.131298","title":"Convergence of batch gradient descent with learnable smooth masks for pruning feedforward neural networks","year":2025,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec à Rimouski","funders":"","keywords":"Convergence (economics); Gradient descent; Pruning; Artificial neural network; Feed forward; Computer science; Feedforward neural network; Stochastic gradient descent; Mathematics; Artificial intelligence; Algorithm; Mathematical optimization; Control theory (sociology); Control (management); Biology; Control engineering","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0001777571,0.000173744,0.000229635,0.00007735661,0.0003147039,0.00009634185,0.0007327599,0.00004234356,0.000001325793],"category_scores_gemma":[0.00001264222,0.0001517796,0.00008247776,0.0007576152,0.00005675209,0.0001473848,0.0002964992,0.0002094052,6.73661e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002346616,"about_ca_system_score_gemma":0.00004266165,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000221609,"about_ca_topic_score_gemma":0.000004856554,"domain_scores_codex":[0.9985274,0.00004064842,0.0003340853,0.0004922712,0.0001550981,0.0004504796],"domain_scores_gemma":[0.9989548,0.0002239792,0.0001953703,0.0004194355,0.0001298607,0.00007652536],"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":[0.00002742998,0.00008448851,0.006733164,0.0001026676,0.00002397653,0.000005462041,0.0001291805,0.862623,0.0009859399,0.04609242,0.0007355314,0.08245672],"study_design_scores_gemma":[0.0003406561,0.0001218052,0.004465484,0.00007266641,0.00001501032,0.000006083484,0.00001324418,0.9914351,0.000884752,0.0002875695,0.00221959,0.0001380393],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09761009,0.00009802735,0.9001598,0.0008406797,0.0003279264,0.0005449977,6.138257e-7,0.000133188,0.0002846222],"genre_scores_gemma":[0.973502,0.000007255273,0.02564755,0.0005462994,0.0000773717,0.00004097703,0.000001871261,0.00001328466,0.0001633255],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.875892,"threshold_uncertainty_score":0.6189394,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01112585937056855,"score_gpt":0.2405622933400859,"score_spread":0.2294364339695174,"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."}}