{"id":"W4327559110","doi":"10.1016/j.cviu.2023.103682","title":"Grow-push-prune: Aligning deep discriminants for effective structural network compression","year":2023,"lang":"en","type":"article","venue":"Computer Vision and Image Understanding","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; MNIST database; Pruning; Artificial intelligence; Deep learning; Machine learning; Construct (python library); Residual; Set (abstract data type); Algorithm","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":[0.0008887165,0.001495959,0.0009380722,0.001525864,0.0006420182,0.0008870732,0.001489927,0.001407239,0.005972534],"category_scores_gemma":[0.004315522,0.0007104232,0.0005721053,0.001217719,0.0007123812,0.002214734,0.001944025,0.002814653,0.002717865],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005561376,"about_ca_system_score_gemma":0.001070426,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002845275,"about_ca_topic_score_gemma":0.008525753,"domain_scores_codex":[0.9995665,0.00007589433,0.00002435455,0.0001222674,0.0001487873,0.00006218487],"domain_scores_gemma":[0.9989218,0.0003589696,0.0000714799,0.000299305,0.0002606699,0.00008785314],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004571758,0.0002174865,0.0009148964,0.00009612225,0.00004555014,0.000152606,0.0001273836,0.05054125,0.03795861,0.01230099,0.01459524,0.8825926],"study_design_scores_gemma":[0.00004110327,0.0001149725,0.0003080882,0.00001793916,0.00001943232,0.000113913,0.00006159226,0.9552854,0.02156666,0.01828235,0.004172092,0.00001661297],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0484342,0.0005849947,0.9403723,0.0004215939,0.0002135855,0.00009688109,0.000412612,0.006586368,0.002877456],"genre_scores_gemma":[0.3268782,0.0003902694,0.6610301,0.0003335026,0.0001400196,0.0001492973,0.001640096,0.001404129,0.008034521],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005972534,"threshold_uncertainty_score":0.01998013,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0348156777220367,"score_gpt":0.3205194251396037,"score_spread":0.285703747417567,"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."}}