{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001003425,0.001051548,0.001335192,0.001568033,0.0007043295,0.001329737,0.002293759,0.001537505,0.004714324],"category_scores_gemma":[0.003767203,0.0007251826,0.001046202,0.001238139,0.0007222013,0.001847221,0.001210559,0.001761652,0.00126362],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007068228,"about_ca_system_score_gemma":0.001363488,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003272822,"about_ca_topic_score_gemma":0.006232567,"domain_scores_codex":[0.9993193,0.00009863306,0.00006726312,0.0001326246,0.0003037889,0.00007832592],"domain_scores_gemma":[0.9985772,0.0006104802,0.0001253439,0.0002127534,0.000420223,0.00005399891],"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":[0.0004422422,0.000099122,0.0006899531,0.0002626999,0.0001798056,0.0003544216,0.0001115683,0.3020158,0.02963086,0.01979412,0.008884159,0.6375353],"study_design_scores_gemma":[0.00003013803,0.00005665984,0.0001423582,0.00002419025,0.00002487636,0.0001641487,0.0000145508,0.9788237,0.01098392,0.005928915,0.003789902,0.00001669734],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006034784,0.0002532352,0.9916778,0.00005881,0.00006579608,0.00005714643,0.00006752858,0.0008433682,0.0009416019],"genre_scores_gemma":[0.05419241,0.000260341,0.9405002,0.0001275682,0.00004900673,0.0001527862,0.0004790011,0.0003369956,0.00390179],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004714324,"threshold_uncertainty_score":0.01577091,"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."}}