{"id":"W2019550707","doi":"10.1016/j.ijar.2013.01.012","title":"A granular neural network: Performance analysis and application to re-granulation","year":2013,"lang":"en","type":"article","venue":"International Journal of Approximate Reasoning","topic":"Rough Sets and Fuzzy Logic","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Granular computing; Granularity; Granulation; Computer science; Artificial neural network; Benchmark (surveying); Artificial intelligence; Backpropagation; Key (lock); Engineering; Rough set","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.00047027,0.0001034334,0.0002015791,0.0002950687,0.00008567836,0.0003698372,0.0006344505,0.00003628555,0.000009952635],"category_scores_gemma":[0.00003462279,0.00008402415,0.00009029844,0.0005242325,0.00001829693,0.0008962054,0.00014616,0.0001232162,0.000008040352],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004666584,"about_ca_system_score_gemma":0.00001574749,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004465798,"about_ca_topic_score_gemma":0.000002843666,"domain_scores_codex":[0.998781,0.00003662417,0.0003772885,0.0001817875,0.0004372733,0.0001860879],"domain_scores_gemma":[0.998951,0.00004571687,0.0003221064,0.0001698533,0.0003985013,0.0001128262],"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":[0.00006405337,0.00007809231,0.1597944,0.0000173896,0.000417047,0.00002127879,0.001152581,0.2111515,0.0007424328,0.01094206,0.0004998875,0.6151192],"study_design_scores_gemma":[0.0001951708,0.00005255802,0.1659786,0.00002647394,0.00003308086,0.00006290718,0.00001689262,0.8315601,0.00006856301,0.001609589,0.0003072428,0.00008879526],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3890549,0.00008445148,0.608584,0.001505468,0.0001736445,0.0000998765,5.24012e-7,0.00002085611,0.0004762176],"genre_scores_gemma":[0.8607793,0.00005391455,0.1386289,0.0002753742,0.000238683,0.000008805694,0.000003441864,0.000004798977,0.000006719477],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6204086,"threshold_uncertainty_score":0.3566348,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008405704641865835,"score_gpt":0.2426832183978554,"score_spread":0.2342775137559896,"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."}}