{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005596992,0.000894366,0.001008137,0.000458755,0.0003165078,0.001007424,0.001029583,0.0008946736,0.00427511],"category_scores_gemma":[0.002838895,0.0004677499,0.0003967881,0.0007218276,0.0006211317,0.001640388,0.001324421,0.00183639,0.0008048858],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005875438,"about_ca_system_score_gemma":0.0008011388,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00230036,"about_ca_topic_score_gemma":0.006695762,"domain_scores_codex":[0.9996471,0.00008225004,0.00001745965,0.00004523811,0.0001491865,0.00005864875],"domain_scores_gemma":[0.9989286,0.0007151254,0.00005528467,0.0001233747,0.0001446514,0.00003292251],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002892554,0.0001201523,0.0004474932,0.0002122428,0.00008253304,0.0001524647,0.00006669492,0.4739931,0.0152965,0.06037581,0.01202722,0.4369365],"study_design_scores_gemma":[0.000007346181,0.00002020733,0.00004822292,0.00001090757,0.00000760951,0.00003099304,0.000005612255,0.9834353,0.002017302,0.01360167,0.0008110033,0.000003725577],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009827496,0.0005980187,0.986074,0.0001934089,0.0000695069,0.00001655457,0.0001097446,0.0005483135,0.002563022],"genre_scores_gemma":[0.4506607,0.001352336,0.5340443,0.0002969134,0.0002449645,0.0001383056,0.0007385183,0.0002969273,0.01222702],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00427511,"threshold_uncertainty_score":0.01430166,"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."}}