{"id":"W2166958963","doi":"10.1142/s0218488505003746","title":"FUZZY RULE EXTRACTION FROM A FEED FORWARD NEURAL NETWORK BY TRAINING A REPRESENTATIVE FUZZY NEURAL NETWORK USING GRADIENT DESCENT","year":2005,"lang":"en","type":"article","venue":"International Journal of Uncertainty Fuzziness and Knowledge-Based Systems","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Thompson Rivers University","funders":"","keywords":"Artificial neural network; Gradient descent; Defuzzification; Fuzzy number; Fuzzy logic; Transformation (genetics); Measure (data warehouse); Membership function; Mathematics; Neuro-fuzzy; Artificial intelligence; Fuzzy classification; Computer science; Function (biology); Fuzzy set; Pattern recognition (psychology); Data mining; Fuzzy control 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":[0.001028112,0.0009758854,0.001135743,0.001263129,0.0005666043,0.001113536,0.0008742308,0.001054216,0.004062031],"category_scores_gemma":[0.003455631,0.0006786612,0.001055526,0.0008711648,0.0003614475,0.0008171608,0.0004157093,0.001188787,0.001317531],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007675842,"about_ca_system_score_gemma":0.001267841,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006136085,"about_ca_topic_score_gemma":0.006828727,"domain_scores_codex":[0.9995697,0.00006404264,0.00004527975,0.000118214,0.0001627841,0.00004000004],"domain_scores_gemma":[0.9990045,0.0003542082,0.00005310552,0.0001197263,0.0004448388,0.0000235697],"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":[0.0002124888,0.0001511768,0.001287886,0.0003261685,0.0001117819,0.0004189613,0.0002248826,0.4443861,0.02658358,0.003691111,0.00252129,0.5200846],"study_design_scores_gemma":[0.00001579734,0.00007335113,0.0006118027,0.0000382694,0.00003199798,0.00008110607,0.00003230447,0.9839244,0.01163968,0.002112105,0.00142482,0.00001444167],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02563521,0.0001610997,0.9696448,0.00007724932,0.00005133866,0.0002470277,0.0001745079,0.00166129,0.002347475],"genre_scores_gemma":[0.2058752,0.0001816996,0.7897096,0.00006448605,0.00001845781,0.000368766,0.0006002249,0.00009773982,0.003083875],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006136085,"threshold_uncertainty_score":0.01358885,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03643321490396093,"score_gpt":0.3062558588690791,"score_spread":0.2698226439651182,"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."}}