{"id":"W4393435355","doi":"10.32604/cmc.2024.048787","title":"Alternative Method of Constructing Granular Neural Networks","year":2024,"lang":"en","type":"article","venue":"Computers, materials & continua/Computers, materials & continua (Print)","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Interpretability; Granular computing; Granularity; Computer science; Artificial neural network; Data mining; Interval (graph theory); Process (computing); Artificial intelligence; Fuzzy logic; Machine learning; Algorithm; Rough set; Mathematics","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","scholarly_communication"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.002557639,0.001473422,0.002636858,0.0006205795,0.0004092903,0.004016659,0.004211626,0.0004912937,0.0003358203],"category_scores_gemma":[0.00007865603,0.001420218,0.0005893175,0.001110241,0.0004872153,0.001735307,0.003111548,0.0005869509,0.0001665644],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001677857,"about_ca_system_score_gemma":0.0001475462,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004099527,"about_ca_topic_score_gemma":0.00001284941,"domain_scores_codex":[0.9900065,0.001375163,0.003157481,0.002744613,0.000891726,0.001824485],"domain_scores_gemma":[0.9937379,0.001485843,0.001450372,0.002277579,0.0005832785,0.000464992],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002300214,0.0003204934,0.0001798792,0.0008695627,0.000891281,0.0006755286,0.001929036,0.004078893,0.6141477,0.164837,0.01303038,0.1988102],"study_design_scores_gemma":[0.003914881,0.0007203614,0.001221833,0.003243678,0.0004591292,0.001501,0.0001584948,0.3203222,0.6237029,0.01215743,0.0283219,0.00427617],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2198157,0.0006409137,0.7556723,0.0007648933,0.01975873,0.001601431,0.0001754201,0.001360371,0.0002102294],"genre_scores_gemma":[0.7956852,0.0001355843,0.1991827,0.0006706644,0.003655244,0.0001853805,0.0001481961,0.000183162,0.0001539325],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5758695,"threshold_uncertainty_score":0.9998015,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01412023348945132,"score_gpt":0.2652711569541157,"score_spread":0.2511509234646644,"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."}}