{"id":"W4387761026","doi":"10.1109/ipccc59175.2023.10253877","title":"Evaluation of Pruning Techniques","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"British Columbia Institute of Technology","funders":"","keywords":"Pruning; Computer science; Memory footprint; Speedup; Inference; Convolutional neural network; Computation; Artificial intelligence; Contextual image classification; Machine learning; Parallel computing; Image (mathematics); 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005591763,0.00002521232,0.00003249321,0.00005464974,0.00002755019,0.000006726847,0.0002344821,0.00001109173,0.000007163692],"category_scores_gemma":[0.00003501988,0.0000225533,0.00001102503,0.0007152895,0.000009996931,0.0001490326,0.00009452608,0.00002108681,0.00003258525],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001271097,"about_ca_system_score_gemma":0.00002142851,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000154189,"about_ca_topic_score_gemma":0.000001358951,"domain_scores_codex":[0.9994548,0.00002720305,0.00007659767,0.0001006821,0.0002768182,0.00006388344],"domain_scores_gemma":[0.9995161,0.00004339549,0.00003228802,0.0002490248,0.000147033,0.00001211605],"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":[1.350966e-7,0.000006861915,0.00005141336,0.00000150303,0.00000231961,1.289458e-7,0.00008210112,0.002169809,0.01638099,0.1558386,0.001448395,0.8240177],"study_design_scores_gemma":[0.00004308723,0.00001328338,0.00143246,0.000005466722,0.000004124608,8.944617e-7,0.000007854235,0.7886155,0.1131243,0.09433488,0.002368709,0.00004944535],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009889673,0.00001359264,0.96985,0.0006966092,0.00002809599,0.0002101631,1.591119e-7,0.0007648292,0.0185469],"genre_scores_gemma":[0.8445802,0.000008370785,0.1550984,0.0000438975,0.00001409931,0.00007008535,9.894335e-7,0.000002574916,0.0001813423],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8346906,"threshold_uncertainty_score":0.09196969,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08284009450376618,"score_gpt":0.3678937605204616,"score_spread":0.2850536660166954,"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."}}