{"id":"W2098087097","doi":"10.1109/lsp.2002.804133","title":"Natural gradient learning neural networks for adaptive inversion of Hammerstein systems","year":2002,"lang":"en","type":"article","venue":"IEEE Signal Processing Letters","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Gradient descent; Backpropagation; Adaptive filter; Artificial neural network; Kernel adaptive filter; Computer science; Multilayer perceptron; Nonlinear system; Activation function; Adaptive system; Inversion (geology); Perceptron; Algorithm; Adaptive algorithm; Adaptive learning; Filter (signal processing); Control theory (sociology); Artificial intelligence; Filter design","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":[0.0001273821,0.0001593879,0.0001924749,0.00007940601,0.0003107273,0.0001410748,0.0004577478,0.00004669354,0.000001369495],"category_scores_gemma":[0.000003922841,0.0001425686,0.0000967196,0.0003923179,0.00007976569,0.0004022178,0.00004631157,0.0002591352,0.000002176188],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003980756,"about_ca_system_score_gemma":0.000006764886,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001408197,"about_ca_topic_score_gemma":7.105127e-7,"domain_scores_codex":[0.9987504,0.0000553901,0.0002675015,0.000360797,0.0002178833,0.0003480118],"domain_scores_gemma":[0.9993107,0.0001197014,0.0002536315,0.0001531148,0.00008798531,0.00007489271],"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":[0.00002110262,0.00004157046,0.0000526956,0.00007202748,0.00002087287,0.000006371992,0.0004621113,0.870159,0.02760876,0.0005724897,0.007550262,0.09343269],"study_design_scores_gemma":[0.0002547126,0.00008859162,0.00001260387,0.00008114795,0.00001130208,0.000008435621,0.00003321961,0.9981104,0.0007922793,0.00003022513,0.0004113899,0.0001657232],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05448506,0.00095889,0.9417531,0.001912952,0.000424021,0.0003163934,9.104127e-7,0.0001132212,0.00003547046],"genre_scores_gemma":[0.9962157,0.000005064465,0.002691082,0.0007053528,0.0002476591,0.00004026771,0.000002390472,0.00001424032,0.00007826406],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9417306,"threshold_uncertainty_score":0.5813779,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02519008230801976,"score_gpt":0.2214355908204638,"score_spread":0.196245508512444,"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."}}