{"id":"W2908960046","doi":"10.1016/j.asoc.2019.01.013","title":"Granular neural networks: A study of optimizing allocation of information granularity in input space","year":2019,"lang":"en","type":"article","venue":"Applied Soft Computing","topic":"Rough Sets and Fuzzy Logic","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"Communication University of China; Chinese Service Center for Scholarly Exchange; National Natural Science Foundation of China; National Science Foundation","keywords":"Granularity; Computer science; Artificial neural network; Space (punctuation); Granular computing; Data mining; Artificial intelligence; Rough set; Operating system","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003843927,0.0006778067,0.001621247,0.0007383684,0.0004702854,0.00284044,0.00161288,0.001592786,0.00186139],"category_scores_gemma":[0.01649163,0.0006941245,0.0005512409,0.00159739,0.001665111,0.003705853,0.001314007,0.001462604,0.00008241908],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002009039,"about_ca_system_score_gemma":0.001232247,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003939439,"about_ca_topic_score_gemma":0.002386492,"domain_scores_codex":[0.998744,0.0006556383,0.00006364065,0.0001800578,0.0002383128,0.0001183691],"domain_scores_gemma":[0.9936342,0.005031244,0.0005245732,0.0003183324,0.0003351504,0.0001564888],"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":[0.0001435752,0.00005302103,0.0005308316,0.0001369026,0.00008004585,0.00005033195,0.00009537662,0.8781984,0.001043958,0.09744751,0.0004560321,0.02176388],"study_design_scores_gemma":[0.00001369512,0.00002379401,0.0001020469,0.00001467823,0.0000124365,0.000006094366,0.0000159353,0.969893,0.0002489633,0.02951127,0.0001521009,0.000005848611],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1094922,0.001726271,0.8818181,0.0009950451,0.0000975498,0.00008371862,0.00007485061,0.0001184563,0.005593828],"genre_scores_gemma":[0.8859953,0.001073954,0.1103955,0.0001233207,0.00009740743,0.0001142192,0.00004916983,0.00006435016,0.002086793],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003939439,"threshold_uncertainty_score":0.02032888,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009168905898712198,"score_gpt":0.2181626742810361,"score_spread":0.2089937683823239,"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."}}