{"id":"W2150035213","doi":"10.1109/72.991413","title":"Optimization-based learning with bounded error for feedforward neural networks","year":2002,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Backpropagation; Artificial neural network; Robustness (evolution); Feedforward neural network; Feed forward; Rprop; Convergence (economics); Bounded function; Artificial intelligence; Algorithm; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001363428,0.0004645059,0.0003706261,0.0001600582,0.001271903,0.0004609587,0.0007973245,0.0002043477,0.00009189582],"category_scores_gemma":[0.000003583249,0.0004066867,0.000280186,0.001197143,0.0001298618,0.0005560308,0.000005632036,0.0008530389,0.000007754143],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006819369,"about_ca_system_score_gemma":0.00001748625,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001108819,"about_ca_topic_score_gemma":0.00003401913,"domain_scores_codex":[0.9973701,0.0001126358,0.0004602444,0.0008616049,0.0003334169,0.0008619498],"domain_scores_gemma":[0.9981323,0.0004789871,0.0002149277,0.0007132787,0.0001689879,0.0002915277],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006497209,0.0001474894,0.00001935282,0.000006614123,0.00003045683,0.000006077547,0.00002574099,0.967257,0.000004047789,0.0001713334,0.0007496957,0.03151721],"study_design_scores_gemma":[0.001130518,0.0005844863,0.00001435209,0.00002730668,0.00005369875,0.00002673158,0.000006638098,0.9966173,0.00005452249,0.00002279421,0.0009726739,0.0004889579],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0009834364,0.0001187944,0.993652,0.002592446,0.0008258133,0.000970213,0.00000634796,0.0007199324,0.0001310044],"genre_scores_gemma":[0.9704875,0.00004395219,0.02621274,0.001751845,0.0003098686,0.0005255694,0.00001611077,0.00007570863,0.0005767073],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9695041,"threshold_uncertainty_score":0.9998385,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02150330613824146,"score_gpt":0.2317074251586706,"score_spread":0.2102041190204291,"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."}}