{"id":"W1689346920","doi":"10.1109/iscas.1993.394248","title":"A new algorithm for training multilayer feedforward neural networks","year":2002,"lang":"en","type":"article","venue":"1993 IEEE International Symposium on Circuits and Systems","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Backpropagation; Artificial neural network; Computer science; Algorithm; Feedforward neural network; Feed forward; Sigmoid function; Rprop; Limiting; Process (computing); Artificial intelligence; Training (meteorology); Function (biology); Probabilistic neural network; Separable space; Time delay neural network; Types of artificial neural networks; Mathematics; Engineering","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":[0.0001621465,0.0001978812,0.0002193678,0.00006789177,0.0001991128,0.0004913101,0.0006129276,0.00008601442,0.00001135894],"category_scores_gemma":[0.000005091507,0.0001740905,0.0001057759,0.0001450819,0.00001995423,0.0002994277,0.00004110429,0.0001417423,0.0000140612],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004531039,"about_ca_system_score_gemma":0.000008373889,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006996001,"about_ca_topic_score_gemma":0.000004457918,"domain_scores_codex":[0.9984756,0.00002882116,0.0003565026,0.0005016691,0.0003125217,0.0003249201],"domain_scores_gemma":[0.9990937,0.0002005678,0.0001512585,0.0002636995,0.00009633364,0.0001944425],"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":[0.000003168592,0.00007647844,0.00008653467,0.00001039679,0.00008929629,0.00001010986,0.0006913357,0.05360036,0.0007452601,0.02800915,0.0197023,0.8969756],"study_design_scores_gemma":[0.0005216256,0.00008762054,0.00007069334,0.00003667585,0.000006595783,0.00006787703,0.00001831314,0.9635369,0.00003140614,0.00009175408,0.03533172,0.0001988227],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001803296,0.0002763478,0.988429,0.002785348,0.003988716,0.0005372693,0.00002443119,0.0001407016,0.002014954],"genre_scores_gemma":[0.9920824,0.00007457371,0.001638325,0.0006264776,0.002083564,0.0001522693,0.000009562857,0.00002161266,0.003311228],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9902791,"threshold_uncertainty_score":0.7099204,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05615242375691548,"score_gpt":0.2712902085578993,"score_spread":0.2151377848009838,"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."}}