{"id":"W3034550700","doi":"10.1109/globecom42002.2020.9322333","title":"A Framework for Neural Network Pruning Using Gibbs Distributions","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Model Reduction and Neural Networks","field":"Physics and Astronomy","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Fujitsu","keywords":"Artificial neural network; Computer science; Pruning; Regularization (linguistics); Artificial intelligence; Machine learning; Simulated annealing","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":[0.0000726572,0.0003236436,0.0003920528,0.00002256386,0.0003337462,0.0001776515,0.0002525322,0.0001952232,0.0005283302],"category_scores_gemma":[0.00001010718,0.0003137507,0.0004133584,0.0001581746,0.00004286475,0.00005912533,0.0004349058,0.0009985116,0.00000748111],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003430184,"about_ca_system_score_gemma":0.0001100211,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006413608,"about_ca_topic_score_gemma":6.932309e-7,"domain_scores_codex":[0.9984834,0.00004631959,0.0003483347,0.0005450893,0.0001218454,0.000454967],"domain_scores_gemma":[0.9990577,0.0001149018,0.0002203811,0.000338302,0.00007747193,0.0001912915],"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":[0.00003372746,0.00004274378,0.0008113446,0.0000446077,0.0001646192,6.966281e-7,0.00006085461,0.5657973,0.00002961156,0.4137208,0.01136716,0.00792654],"study_design_scores_gemma":[0.000128734,0.00001566535,0.00003837712,0.0001100963,0.00009825429,6.688237e-7,0.00004545617,0.7120548,0.00007460013,0.2817183,0.005385094,0.0003299081],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01257585,0.00007050819,0.981611,0.00156985,0.00186146,0.0007055898,0.0002175058,0.0001380892,0.001250113],"genre_scores_gemma":[0.8826076,0.000003251523,0.1090655,0.0002169306,0.007050802,0.0001340864,0.0006648321,0.00004732312,0.000209648],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8725455,"threshold_uncertainty_score":0.9999315,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09070092212850571,"score_gpt":0.3403571070044715,"score_spread":0.2496561848759657,"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."}}