{"id":"W2979766873","doi":"10.1109/fuzz-ieee.2019.8858809","title":"Improved Deep Fuzzy Clustering for Accurate and Interpretable Classifiers","year":2019,"lang":"en","type":"article","venue":"","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Artificial intelligence; Interpretability; Computer science; Cluster analysis; Deep learning; MNIST database; Machine learning; Fuzzy logic; Fuzzy clustering; Classifier (UML); Neuro-fuzzy; Artificial neural network; Data mining; Pattern recognition (psychology); 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00005902459,0.00006102182,0.00007285173,0.0000175048,0.00005691813,0.0001481953,0.0002520991,0.00002419824,0.000007978358],"category_scores_gemma":[0.000002961152,0.00004867016,0.0000241264,0.00007983896,0.00001004392,0.0002874766,0.0001744357,0.00004122874,0.00001174045],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007358054,"about_ca_system_score_gemma":0.00000726001,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007577525,"about_ca_topic_score_gemma":0.00001468073,"domain_scores_codex":[0.9994932,0.000004860916,0.00009010735,0.0002230252,0.00003091318,0.0001578442],"domain_scores_gemma":[0.9996033,0.00006193109,0.00003008672,0.0002355825,0.00002041634,0.00004872311],"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":[0.00004246891,0.0000609489,0.0006007096,0.0001187592,0.00005311716,9.006508e-7,0.0006374617,0.003446406,0.08180039,0.3751394,0.005170332,0.5329291],"study_design_scores_gemma":[0.0001725136,0.00003867092,0.000117612,0.000004550707,0.000001555313,0.000002421976,0.00002019508,0.9913857,0.0005685861,0.002162208,0.005447129,0.00007886629],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01159749,0.00002840993,0.9818118,0.0009010347,0.0001726713,0.0003185302,6.019629e-7,0.00007883689,0.005090611],"genre_scores_gemma":[0.9391092,0.000009427248,0.05790454,0.0006461634,0.00002845605,0.00004839091,8.407826e-7,0.000005035829,0.002247942],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9879393,"threshold_uncertainty_score":0.1984712,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01398455070607914,"score_gpt":0.248353111908802,"score_spread":0.2343685612027229,"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."}}