{"id":"W2160354731","doi":"10.1155/s1110865704405010","title":"A Neural Network MLSE Receiver Based on Natural Gradient Descent: Application to Satellite Communications","year":2004,"lang":"en","type":"article","venue":"EURASIP Journal on Advances in Signal Processing","topic":"Blind Source Separation Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Viterbi algorithm; Channel (broadcasting); Multipath propagation; Maximum likelihood sequence estimation; Gradient descent; Estimator; Algorithm; Electronic engineering; Telecommunications; Artificial neural network; Estimation theory; Artificial intelligence; Engineering; Mathematics; Statistics; Decoding methods","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":[0.0007979352,0.0002230594,0.0002042707,0.0003356049,0.000463373,0.0004068477,0.001339746,0.00005521275,0.000002051444],"category_scores_gemma":[0.00005059664,0.0001987576,0.00007356627,0.001189399,0.00007047976,0.001386699,0.0001057353,0.0008788843,0.00002066609],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003498525,"about_ca_system_score_gemma":0.0001273113,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001694164,"about_ca_topic_score_gemma":0.00001984392,"domain_scores_codex":[0.997959,0.0002512743,0.0005089393,0.0003810461,0.0005142496,0.0003855488],"domain_scores_gemma":[0.9986031,0.0001639422,0.0003541409,0.0005230625,0.0001840554,0.0001716682],"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":[0.00009344963,0.0002017375,0.0003508455,0.00001153049,0.000002087781,0.00001507897,0.0007307645,0.377326,0.0003204938,0.007121595,0.00001767881,0.6138087],"study_design_scores_gemma":[0.002648856,0.001617163,0.008204605,0.002698112,0.00001545729,0.0002237424,0.0001366785,0.8458256,0.005236173,0.06239786,0.06970037,0.001295368],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004913034,0.004124319,0.9815632,0.006957932,0.0001912964,0.0004205359,6.89364e-7,0.000220587,0.001608387],"genre_scores_gemma":[0.848885,0.0003253861,0.1454789,0.005142215,0.0001068771,0.0000315062,0.000003001962,0.00001710754,0.000009937822],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.843972,"threshold_uncertainty_score":0.8105099,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01725542566618462,"score_gpt":0.3089235447865316,"score_spread":0.291668119120347,"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."}}