{"id":"W2133539287","doi":"10.1109/tcomm.2005.843416","title":"Kalman Filter-Trained Recurrent Neural Equalizers for Time-Varying Channels","year":2005,"lang":"en","type":"article","venue":"IEEE Transactions on Communications","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":75,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; University of Ottawa","funders":"","keywords":"Kalman filter; Recurrent neural network; Extended Kalman filter; Computer science; Convergence (economics); Control theory (sociology); Equalization (audio); Channel (broadcasting); Artificial neural network; Gradient descent; Invariant extended Kalman filter; Artificial intelligence; Telecommunications","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":[0.0001931579,0.000197703,0.0001801522,0.0001495999,0.001056788,0.0001653477,0.002056968,0.00007036271,0.00004599899],"category_scores_gemma":[0.000005146927,0.0002039424,0.0002044852,0.000518541,0.00009518604,0.0004741278,0.00001847277,0.0003150003,0.00014837],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007339402,"about_ca_system_score_gemma":0.00003949421,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009920768,"about_ca_topic_score_gemma":0.00002880872,"domain_scores_codex":[0.9986365,0.0001076037,0.0003794311,0.0003657798,0.0001649886,0.0003456368],"domain_scores_gemma":[0.996869,0.0005563169,0.0001133411,0.002207299,0.0001101673,0.0001439226],"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":[0.00003109808,0.001426731,9.281689e-7,0.00002047021,0.0001032972,4.989117e-7,0.001463464,0.1321172,0.006040367,0.03068307,0.01025771,0.8178552],"study_design_scores_gemma":[0.000478419,0.0001071215,0.000004999341,0.00002789512,0.00002520109,0.000008365128,0.00001416585,0.9366925,0.003101575,0.001067943,0.0582007,0.0002711464],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005093041,0.0001271923,0.9704174,0.02634124,0.0003158259,0.000694188,0.00005855041,0.0003959749,0.001140333],"genre_scores_gemma":[0.9165272,0.0001731468,0.07988449,0.001055544,0.0001117686,0.0009074826,0.00002933723,0.00002623349,0.001284826],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9160179,"threshold_uncertainty_score":0.8316528,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06137283117714596,"score_gpt":0.314436738160239,"score_spread":0.2530639069830931,"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."}}