{"id":"W4226453938","doi":"10.1109/lsp.2022.3164328","title":"A Low-Complexity Modified ThiNet Algorithm for Pruning Convolutional Neural Networks","year":2022,"lang":"en","type":"article","venue":"IEEE Signal Processing Letters","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Pruning; Convolutional neural network; Computer science; Algorithm; Reduction (mathematics); Layer (electronics); Computational complexity theory; Norm (philosophy); Time complexity; Artificial intelligence; Pattern recognition (psychology); Mathematics","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","sts"],"consensus_categories":[],"category_scores_codex":[0.0002869245,0.0002334529,0.0002093191,0.00009965121,0.001504619,0.0001860048,0.001144879,0.00003617231,0.00001110604],"category_scores_gemma":[0.000005131414,0.0002569459,0.0001045823,0.0006701214,0.000161077,0.0005855094,0.0002571928,0.0004784332,0.000001874706],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001574387,"about_ca_system_score_gemma":0.00007332747,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006147031,"about_ca_topic_score_gemma":7.774498e-7,"domain_scores_codex":[0.9978616,0.00009470517,0.000336762,0.0006693218,0.0004484846,0.0005891562],"domain_scores_gemma":[0.9990471,0.000188613,0.0002527892,0.0003103073,0.00008707196,0.0001141072],"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":[0.00001460023,0.00005266222,0.000006515862,0.00001634746,0.000007305777,0.00000794067,0.0001281966,0.853097,0.004656269,0.001425725,0.002406066,0.1381814],"study_design_scores_gemma":[0.0004492119,0.00005357719,0.00005140836,0.000009464889,0.000008645298,0.00004607898,0.00001070046,0.9941445,0.0003024421,0.004072916,0.0005511861,0.0002998741],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004522973,0.0001330133,0.9897553,0.004278887,0.0003703493,0.0005033028,0.00002089575,0.0003881914,0.00002714017],"genre_scores_gemma":[0.8227643,5.110105e-7,0.1679591,0.008172404,0.000459324,0.0005343006,0.00004086579,0.00002976493,0.00003947296],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8217962,"threshold_uncertainty_score":0.9999883,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03640269422525121,"score_gpt":0.2676957059784854,"score_spread":0.2312930117532341,"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."}}