{"id":"W2120439140","doi":"10.1109/icnn.1993.298746","title":"Minimum description length pruning and maximum mutual information training of adaptive probabilistic neural networks","year":2002,"lang":"en","type":"article","venue":"IEEE International Conference on Neural Networks","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Minimum description length; Probabilistic logic; Pruning; Artificial neural network; Computer science; Artificial intelligence; Gaussian; Benchmark (surveying); Mutual information; Probabilistic neural network; Machine learning; Pattern recognition (psychology); Algorithm; Time delay neural network","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":[0.0001907816,0.0002975502,0.0002844277,0.0001697897,0.0001887393,0.0003687321,0.0008036863,0.0001424353,0.00004735715],"category_scores_gemma":[0.00003671342,0.0002808238,0.00009252736,0.0003479815,0.0001667841,0.001634939,0.0001484712,0.0005121076,0.000007358455],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005435382,"about_ca_system_score_gemma":0.00001592415,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001639104,"about_ca_topic_score_gemma":0.000014472,"domain_scores_codex":[0.9979869,0.0001009449,0.0006248013,0.0004413748,0.0004307661,0.0004152505],"domain_scores_gemma":[0.9985626,0.0002183999,0.0004159538,0.0003332371,0.0003155887,0.0001542357],"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":[0.00008931642,0.0001037579,0.0002005194,0.00001089329,0.00005141153,0.00000991151,0.001044127,0.5906687,0.0001738114,0.1081151,0.00139234,0.2981401],"study_design_scores_gemma":[0.0004294956,0.000276229,0.0006083096,0.00007049058,0.00001142944,0.00004329638,0.00009578294,0.9959562,0.00001725213,0.002035405,0.0001925114,0.0002635427],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1903632,0.000141275,0.7970912,0.003016603,0.002705316,0.0008514058,0.00002045537,0.0002876745,0.005522773],"genre_scores_gemma":[0.9973084,0.000108029,0.001427258,0.0005997568,0.0003498183,0.00006656776,0.00002351193,0.00001379122,0.0001028579],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8069451,"threshold_uncertainty_score":0.9999644,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0888738075565767,"score_gpt":0.2649945237197897,"score_spread":0.176120716163213,"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."}}