{"id":"W3135002377","doi":"10.1109/icassp39728.2021.9414434","title":"A Framework for Pruning Deep Neural Networks Using Energy-Based Models","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Fujitsu","keywords":"Pruning; Computer science; Artificial neural network; Deep neural networks; Function (biology); Artificial intelligence; Simple (philosophy); Energy (signal processing); Machine learning; Population; Pattern recognition (psychology); Mathematics; Statistics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001350182,0.0004515765,0.0004674821,0.0001168922,0.0003288577,0.0005568751,0.001796118,0.0004839007,0.00000743132],"category_scores_gemma":[0.00003552299,0.0004759046,0.0003238617,0.0005996262,0.00005152478,0.000400657,0.001907387,0.0007852947,3.475301e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001357008,"about_ca_system_score_gemma":0.000167948,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000312675,"about_ca_topic_score_gemma":0.0000278447,"domain_scores_codex":[0.9971334,0.00008649313,0.0004853718,0.001349541,0.0002830179,0.0006621422],"domain_scores_gemma":[0.9966496,0.0006274864,0.0003582339,0.001908184,0.0002672886,0.0001892334],"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":[0.000003418215,0.00002427101,0.000003256022,0.00002176146,0.00001324672,0.000004032304,0.0000347054,0.7776985,0.00001561394,0.2078532,0.00001471981,0.01431326],"study_design_scores_gemma":[0.0001033959,0.00001196189,0.000001505068,0.00008155143,0.00002124243,0.000004957338,0.000007704904,0.8036728,0.0001442474,0.1954862,0.00005942835,0.0004050302],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003219108,0.0008690257,0.9959625,0.0007090289,0.0008573399,0.0005775627,0.000003170266,0.0005795478,0.000119891],"genre_scores_gemma":[0.3553551,0.00001201753,0.6422908,0.001578777,0.000311858,0.0003466005,0.00004352672,0.00004289124,0.00001840882],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3550332,"threshold_uncertainty_score":0.9997693,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06789464731993908,"score_gpt":0.3146569498918673,"score_spread":0.2467623025719282,"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."}}