{"id":"W4414918096","doi":"10.1007/978-3-032-01536-5_69","title":"Efficient Channel Pruning via Sparse Learning for Compact Deep Neural Networks","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"Wireless Signal Modulation Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec à Rimouski","funders":"","keywords":"Pruning; Benchmark (surveying); Deep learning; Artificial neural network; Channel (broadcasting); Key (lock); Deep neural networks; Computational complexity theory","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000575869,0.0004901725,0.0007171794,0.0002942355,0.0002942414,0.0003766036,0.0004767917,0.0006748874,0.000002361524],"category_scores_gemma":[0.00006204598,0.0004584862,0.0001448668,0.000196684,0.00005964999,0.00007036403,0.0001333984,0.0009240948,0.000001060303],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001578933,"about_ca_system_score_gemma":0.00003128845,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003534437,"about_ca_topic_score_gemma":0.0000461896,"domain_scores_codex":[0.997564,0.0001317184,0.0006832859,0.0008371196,0.0002826643,0.0005012655],"domain_scores_gemma":[0.9975095,0.001195992,0.0005331508,0.0004833648,0.0001649596,0.0001130521],"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":[0.00001721772,0.000008244203,0.00008086014,0.0001013124,0.00003315671,0.00000563356,0.0001717311,0.9553671,0.000003339249,0.01483659,0.00003539274,0.02933937],"study_design_scores_gemma":[0.0003116903,0.00007331103,0.0001123139,0.0006819885,0.00002527787,0.00001564086,0.000002422387,0.9961392,8.634707e-7,0.001006997,0.001211261,0.0004190219],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00004257375,0.007831266,0.9868704,0.0002297862,0.00197668,0.001126137,0.0000015336,0.0001528266,0.001768762],"genre_scores_gemma":[0.996691,0.00004924162,0.0005650407,0.0001175704,0.000941591,0.00004826486,0.00006376741,0.0000490947,0.001474441],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9966484,"threshold_uncertainty_score":0.9997867,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02273304137929728,"score_gpt":0.237190104718876,"score_spread":0.2144570633395788,"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."}}