{"id":"W2158271278","doi":"10.1109/ijcnn.2005.1556039","title":"Comparing \"pattern discovery\" and back-propagation classifiers","year":2006,"lang":"en","type":"article","venue":"Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005.","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Classifier (UML); Artificial intelligence; A priori and a posteriori; Computer science; Backpropagation; Artificial neural network; Pattern recognition (psychology); Machine learning; Separable space; Random subspace method; Data mining; 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":[],"category_scores_codex":[0.0002165034,0.0003789438,0.0003159413,0.0001808686,0.0002430662,0.00139445,0.0008665387,0.0001206564,0.00006860408],"category_scores_gemma":[0.00001018931,0.0003466265,0.0001045503,0.0002223078,0.0001359688,0.001587253,0.0002190684,0.0004682349,0.00007915936],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001317803,"about_ca_system_score_gemma":0.00003021885,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007305777,"about_ca_topic_score_gemma":0.00007856131,"domain_scores_codex":[0.9973607,0.00002106954,0.0005844302,0.0008507128,0.0005380131,0.0006450831],"domain_scores_gemma":[0.9989393,0.00004846629,0.0003662822,0.0002294621,0.0002298866,0.0001865836],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001467488,0.0007203668,0.02566488,0.00007664436,0.0001545153,0.00004108393,0.0001666556,0.08595241,0.01158058,0.6115276,0.1763138,0.08765465],"study_design_scores_gemma":[0.0004625578,0.00005323806,0.008453784,0.0001073806,0.000009468303,0.00005225453,0.00001609549,0.9834687,0.0007315764,0.002070095,0.004167559,0.000407355],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.266208,0.0002037578,0.6665882,0.02484809,0.003209723,0.001132214,0.00002183593,0.0006240477,0.03716406],"genre_scores_gemma":[0.9940341,0.0001876178,0.001299697,0.0009244984,0.001226666,0.00006640361,0.00003114023,0.00002657439,0.002203346],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8975163,"threshold_uncertainty_score":0.9998986,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04935338128072397,"score_gpt":0.2596534632881919,"score_spread":0.210300082007468,"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."}}