{"id":"W3180051575","doi":"10.1109/access.2021.3108545","title":"Taxonomy of Saliency Metrics for Channel Pruning","year":2021,"lang":"en","type":"preprint","venue":"IEEE Access","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Trinity College","funders":"Science Foundation Ireland","keywords":"Pruning; Computer science; Metric (unit); Artificial intelligence; Convolutional neural network; Machine learning; Taxonomy (biology); Reduction (mathematics); Context (archaeology); Computation; Pattern recognition (psychology); Algorithm; 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":[0.004211356,0.001980265,0.0009795752,0.005158301,0.0009080601,0.001927938,0.00148856,0.001451248,0.001634908],"category_scores_gemma":[0.02465891,0.0003708374,0.0007284439,0.002621659,0.001966601,0.004879577,0.002029432,0.001611684,0.0003217125],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001938063,"about_ca_system_score_gemma":0.001052316,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001221521,"about_ca_topic_score_gemma":0.001656399,"domain_scores_codex":[0.9960107,0.0009349548,0.000517228,0.0004380083,0.001906187,0.0001930119],"domain_scores_gemma":[0.9888459,0.005455285,0.001611136,0.001170186,0.002469343,0.0004481681],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004668451,0.0002104422,0.00716413,0.001269154,0.0002485439,0.0002957909,0.0006382178,0.1376653,0.02694613,0.1673499,0.01106444,0.6466811],"study_design_scores_gemma":[0.00007259736,0.001057282,0.007870594,0.0004605031,0.0002464647,0.001158259,0.0003094297,0.7406496,0.03051522,0.1966843,0.02079116,0.0001846558],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.04655543,0.006938035,0.9335137,0.0008451583,0.0002347533,0.0004571665,0.0003287953,0.00124407,0.009882877],"genre_scores_gemma":[0.5396456,0.002967116,0.4533191,0.0002609265,0.0003086007,0.0006191602,0.0005512123,0.0003300384,0.001998231],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.005158301,"threshold_uncertainty_score":0.02227199,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1039471832573742,"score_gpt":0.3452101734254416,"score_spread":0.2412629901680674,"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."}}