{"id":"W2965174861","doi":"10.24963/ijcai.2019/525","title":"COP: Customized Deep Model Compression via Regularized Correlation-Based Filter-Level Pruning","year":2019,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":73,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institute for Advanced Research","keywords":"Computer science; Redundancy (engineering); Normalization (sociology); Convolutional neural network; Pruning; Filter (signal processing); Artificial neural network; Algorithm; Computational complexity theory; Artificial intelligence; Mathematical optimization; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007810151,0.001458851,0.00114325,0.0009483375,0.0004203189,0.001007922,0.002382549,0.001247097,0.003670482],"category_scores_gemma":[0.00291666,0.0005446336,0.0008781621,0.0008644632,0.0005788126,0.001343187,0.001715835,0.001913194,0.001212195],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007476716,"about_ca_system_score_gemma":0.001875564,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005851495,"about_ca_topic_score_gemma":0.01073645,"domain_scores_codex":[0.9995025,0.00005207388,0.00003018191,0.00009717099,0.0002471441,0.00007098477],"domain_scores_gemma":[0.9992446,0.0002415794,0.00008248301,0.0002159243,0.0001730775,0.00004242825],"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":[0.0003750683,0.0002260524,0.002020534,0.0002366812,0.0002386501,0.0004471543,0.0001272059,0.3277775,0.03328565,0.0169628,0.022133,0.5961698],"study_design_scores_gemma":[0.00002339132,0.00003295629,0.0001927897,0.00001225228,0.00002077983,0.00009467172,0.000009430177,0.9859421,0.008381254,0.003263602,0.002018712,0.00000816366],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01849106,0.0004766734,0.9723068,0.0001676245,0.00008859769,0.0001079302,0.0002477918,0.00610341,0.002010069],"genre_scores_gemma":[0.2699903,0.0004532921,0.7201023,0.0005206013,0.0001031611,0.0002991497,0.001987397,0.001319342,0.005224458],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005851495,"threshold_uncertainty_score":0.01227897,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02319882392590332,"score_gpt":0.2510254103924932,"score_spread":0.2278265864665899,"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."}}