{"id":"W4406611623","doi":"10.1109/smc54092.2024.10831075","title":"Novel Post-Training Structure-Agnostic Weight Pruning Technique for Deep Neural Networks","year":2024,"lang":"en","type":"article","venue":"","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Wilfrid Laurier University; Brock University","funders":"","keywords":"Computer science; Pruning; Artificial neural network; Artificial intelligence; Training (meteorology); Deep neural networks; Training set; Machine learning; Pattern recognition (psychology)","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":[0.001270413,0.001656733,0.001101079,0.0007683065,0.0004893745,0.0006995401,0.00208839,0.00119106,0.001174068],"category_scores_gemma":[0.003098658,0.0006060295,0.0007400488,0.0006316798,0.0005844335,0.001187224,0.001057069,0.001989234,0.0004132761],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006872818,"about_ca_system_score_gemma":0.001470524,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00467931,"about_ca_topic_score_gemma":0.009393313,"domain_scores_codex":[0.999359,0.00009868195,0.00005308344,0.0001069959,0.000299472,0.00008275735],"domain_scores_gemma":[0.9992552,0.0002444697,0.0001191969,0.0001114161,0.0002350996,0.00003449192],"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":[0.0002041161,0.0001959431,0.001570593,0.0001559575,0.0001391243,0.0002976035,0.0001362001,0.5061458,0.02989388,0.01055568,0.004872739,0.4458323],"study_design_scores_gemma":[0.00001479993,0.00005194262,0.0002212973,0.00001556429,0.00002120207,0.00005815744,0.000009237752,0.9899995,0.006155109,0.002447477,0.0009993014,0.00000645613],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0294746,0.0007039829,0.9665391,0.0002051667,0.00007212993,0.00008230342,0.00006618168,0.001305624,0.001551096],"genre_scores_gemma":[0.4105053,0.0007269338,0.5825993,0.0004212602,0.0001138888,0.000291978,0.0005199332,0.0003541438,0.004467171],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00467931,"threshold_uncertainty_score":0.009304166,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01458509743804059,"score_gpt":0.2566982081829201,"score_spread":0.2421131107448795,"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."}}