{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00351275,0.00145031,0.0014997,0.0007942485,0.0005999975,0.001208974,0.002552694,0.002223284,0.00383072],"category_scores_gemma":[0.01036824,0.0006636186,0.0006923444,0.0008662542,0.001153272,0.001673903,0.002147981,0.002503003,0.0008729933],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009976209,"about_ca_system_score_gemma":0.001868365,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004693578,"about_ca_topic_score_gemma":0.0129154,"domain_scores_codex":[0.9988482,0.0004312479,0.00006017086,0.0001473496,0.0004042035,0.000108747],"domain_scores_gemma":[0.9973391,0.001543505,0.0001754583,0.0002886606,0.000536954,0.000116344],"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":[0.0002570638,0.0002831029,0.001108613,0.0002141418,0.0001121995,0.000163964,0.0001351792,0.6040971,0.009931582,0.0451507,0.01294887,0.3255974],"study_design_scores_gemma":[0.00000920172,0.00001586744,0.0000560403,0.00001001433,0.000005692571,0.00001048801,0.000004908964,0.9940543,0.000771948,0.004695037,0.0003631872,0.000003425611],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01015438,0.0003746052,0.9862077,0.000297586,0.00008109955,0.00005640502,0.00005371406,0.0006647654,0.002109657],"genre_scores_gemma":[0.3033779,0.0003970932,0.6858889,0.0006384921,0.0002074866,0.0003520397,0.0004223684,0.000654157,0.008061438],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004693578,"threshold_uncertainty_score":0.01857746,"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."}}