{"id":"W4414114940","doi":"10.1007/s10586-025-05504-9","title":"Multiobjective pruning for sparse deep neural networks: leveraging $$L_0$$ regularization on batch normalization scaling factors","year":2025,"lang":"en","type":"article","venue":"Cluster Computing","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":"Normalization (sociology); Regularization (linguistics); Pruning; Convolutional neural network; Deep neural networks; Computational complexity theory; Benchmark (surveying); Scaling","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":[0.0002971251,0.0002231349,0.0002087632,0.0001679275,0.0008618657,0.0004015533,0.0005207002,0.00008938826,8.624849e-7],"category_scores_gemma":[0.00006651763,0.0002213946,0.00009826906,0.0008332661,0.00002793806,0.0003961363,0.0003294879,0.0002011295,0.000001250691],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000105465,"about_ca_system_score_gemma":0.00002206696,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001140807,"about_ca_topic_score_gemma":0.000005521893,"domain_scores_codex":[0.9983379,0.00009796349,0.0004005176,0.0005901136,0.0001543148,0.0004191556],"domain_scores_gemma":[0.998628,0.0005336101,0.0002071502,0.0003936827,0.0001742226,0.00006335273],"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":[0.000007810394,0.00002776318,0.001800393,0.00001855318,0.00001465803,4.614817e-7,0.0007607209,0.9382427,0.00006799518,0.01086368,0.000111282,0.04808401],"study_design_scores_gemma":[0.0004569312,0.00002634593,0.003406374,0.0001184778,0.00001364965,0.000001749936,0.0001012982,0.9940394,0.0004583053,0.0009880179,0.0001783959,0.0002110556],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06413412,0.00004608565,0.9332278,0.00055535,0.0008225291,0.0006738487,7.112706e-7,0.0002774805,0.0002621161],"genre_scores_gemma":[0.9710936,0.000001709177,0.02740709,0.001075777,0.0002438933,0.00002486303,0.00003763113,0.00001911288,0.00009630791],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9069595,"threshold_uncertainty_score":0.9028209,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01815477915609013,"score_gpt":0.2638615001822298,"score_spread":0.2457067210261396,"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."}}