{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002439279,0.001180167,0.001217701,0.0006742876,0.0004785937,0.0007681703,0.001992352,0.002325582,0.003928635],"category_scores_gemma":[0.01053863,0.0008466783,0.0005163673,0.0003982956,0.001022973,0.001404547,0.001349612,0.001828474,0.0009525715],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001006453,"about_ca_system_score_gemma":0.001584693,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006259658,"about_ca_topic_score_gemma":0.007998846,"domain_scores_codex":[0.9994892,0.0001462629,0.00003562109,0.00008680614,0.0001769733,0.00006519249],"domain_scores_gemma":[0.9968637,0.002038406,0.0001469284,0.0002102387,0.0006323631,0.0001084019],"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":[0.0005738236,0.0001451173,0.000847211,0.0002830414,0.00008468124,0.0001329154,0.0001394699,0.7532282,0.01486786,0.02331921,0.005414266,0.2009641],"study_design_scores_gemma":[0.00000775585,0.00001743808,0.00005258218,0.00000716423,0.000003503608,0.000008058457,0.000002344069,0.9971725,0.000995888,0.001575856,0.0001546274,0.000002289042],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02099314,0.0004670808,0.9755224,0.000186707,0.00009533788,0.00006827528,0.00006252088,0.0007258255,0.001878546],"genre_scores_gemma":[0.3834512,0.0002963137,0.6059059,0.000207763,0.00008966175,0.0003026637,0.0003277089,0.0004619376,0.008956937],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006259658,"threshold_uncertainty_score":0.01314259,"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."}}