{"id":"W1958708463","doi":"10.1109/iscas.1992.230013","title":"Convergence and generalization properties of multilayer feedforward neural networks","year":2003,"lang":"en","type":"article","venue":"","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Backpropagation; Generalization; Artificial neural network; Convergence (economics); Rprop; Computer science; Feed forward; Feedforward neural network; Artificial intelligence; Algorithm; Function (biology); Process (computing); Activation function; Mathematics; Types of artificial neural networks; Time delay neural network; Engineering; Control engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.00005949504,0.00006265174,0.00007361574,0.00001788482,0.00006192344,0.00003640339,0.0001503539,0.00002436096,0.00000994558],"category_scores_gemma":[0.000005741386,0.00004609097,0.00001785407,0.0001844562,0.00003773789,0.0001913324,0.00004785845,0.00003418404,0.000001330957],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000002931934,"about_ca_system_score_gemma":0.000006527092,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001682586,"about_ca_topic_score_gemma":0.000005148565,"domain_scores_codex":[0.9994978,0.0000258791,0.0001314784,0.0001620358,0.00006990076,0.0001129187],"domain_scores_gemma":[0.9996715,0.000009938381,0.00004275166,0.0001834,0.0000505462,0.00004183562],"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":[0.000005528087,0.00008886024,0.01380152,0.00003132375,0.0000188768,0.000001361266,0.0003289803,0.1535329,0.02826577,0.7792056,0.002053222,0.02266603],"study_design_scores_gemma":[0.00008148584,0.00001398869,0.0007696601,0.000003760516,0.000001970571,0.00000499601,0.000006027293,0.9837745,0.01425079,0.000242514,0.0007798357,0.00007048652],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2134438,0.0003916889,0.7852128,0.00026847,0.0001135169,0.0001321995,1.505391e-7,0.00005020032,0.0003871853],"genre_scores_gemma":[0.9919785,0.00007323633,0.007409929,0.000253799,0.00001597053,0.00001116412,3.217887e-7,0.000003268571,0.0002538111],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8302416,"threshold_uncertainty_score":0.1879535,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02084182134114359,"score_gpt":0.2180529085774212,"score_spread":0.1972110872362776,"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."}}