{"id":"W4388757355","doi":"10.1007/s12293-023-00402-2","title":"An optimization method for pruning rates of each layer in CNN based on the GA-SMSM","year":2023,"lang":"en","type":"article","venue":"Memetic Computing","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"National Natural Science Foundation of China","keywords":"Pruning; Complex system; Layer (electronics); Computer science; Artificial intelligence; Algorithm; Pattern recognition (psychology); Biological system; Materials science; Nanotechnology; Biology; Botany","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":[],"consensus_categories":[],"category_scores_codex":[0.006396068,0.0001156385,0.0002089035,0.0002343743,0.0001445137,0.00008638271,0.0005655923,0.00004144594,0.000005122806],"category_scores_gemma":[0.0006228682,0.00008965036,0.00006067602,0.001219437,0.00001830646,0.0000921452,0.00008839836,0.0001196636,0.000002276679],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001948519,"about_ca_system_score_gemma":0.00004920701,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003036234,"about_ca_topic_score_gemma":0.000005873234,"domain_scores_codex":[0.9982087,0.0006553259,0.0003107258,0.0003328751,0.0002136251,0.0002787386],"domain_scores_gemma":[0.9961693,0.00309443,0.0001440245,0.0004646361,0.00009757833,0.0000300536],"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":[0.000005799305,0.00003194919,0.002560604,0.00002978602,0.000004772397,0.000001667534,0.0006452897,0.9351616,0.0009908732,0.002371399,0.00002896583,0.05816731],"study_design_scores_gemma":[0.0002970145,0.00008956761,0.009777631,0.00006919905,0.000003140365,5.98753e-7,0.00005147007,0.9831871,0.005526857,0.0008362704,0.00005972041,0.0001013841],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02986721,0.00001483151,0.9683912,0.000909248,0.0002156923,0.0002700818,7.592126e-7,0.0001295946,0.0002013951],"genre_scores_gemma":[0.5248525,6.242655e-7,0.474931,0.0001574954,0.00003181979,0.000008622789,0.000002982535,0.00000842449,0.000006628798],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4949852,"threshold_uncertainty_score":0.3655835,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08347497233303464,"score_gpt":0.3928723355189769,"score_spread":0.3093973631859422,"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."}}