{"id":"W4388430254","doi":"10.1109/tsusc.2023.3330573","title":"Parallel Trajectory Training of Recurrent Neural Network Controllers With Levenberg–Marquardt and Forward Accumulation Through Time in Closed-Loop Control Systems","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Sustainable Computing","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Directorate for Computer and Information Science and Engineering; National Science Foundation","keywords":"Levenberg–Marquardt algorithm; Trajectory; Control theory (sociology); Closed loop; Artificial neural network; Computer science; Loop (graph theory); Control engineering; Control (management); Artificial intelligence; Engineering; Mathematics; Physics","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":[0.001184803,0.0003374721,0.0006934083,0.0003585177,0.000371204,0.0001588232,0.0004092071,0.0001254669,0.00000179767],"category_scores_gemma":[0.00002800354,0.0003253022,0.0001297389,0.001376083,0.0001188071,0.0005951445,0.00001114112,0.0004281837,0.000003728348],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002478371,"about_ca_system_score_gemma":0.0002043104,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002178363,"about_ca_topic_score_gemma":0.0000332072,"domain_scores_codex":[0.9968964,0.0004058919,0.0006613889,0.0006315873,0.0004155868,0.0009891141],"domain_scores_gemma":[0.9978505,0.001084694,0.0003293438,0.0003905533,0.0002367855,0.0001081211],"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":[0.0002487644,0.00006050781,0.0001507192,0.00009328241,0.0001111182,0.00006482163,0.002057738,0.9531767,0.00003021833,0.001519689,0.00002570592,0.0424607],"study_design_scores_gemma":[0.004590063,0.0004851136,0.001162012,0.0001810496,0.00004311873,0.00001914484,0.00173911,0.9911456,0.00000636389,0.0002316964,0.00008634716,0.0003104533],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09037223,0.0001774945,0.9071248,0.0002452022,0.0003863626,0.00126189,0.000004927404,0.0003469498,0.00008012891],"genre_scores_gemma":[0.9934283,0.000008884727,0.006049751,0.00004575308,0.00006184286,0.00008537588,0.000003193717,0.00003541744,0.0002814811],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9030561,"threshold_uncertainty_score":0.9999199,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02807919982157434,"score_gpt":0.2676599859668572,"score_spread":0.2395807861452829,"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."}}