{"id":"W3103714888","doi":"10.1109/ipc47351.2020.9252417","title":"Recurrent neural nets achieving MLSE performance in bandlimited optical channels","year":2020,"lang":"en","type":"article","venue":"","topic":"Optical Network Technologies","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Bandlimiting; Computer science; Recurrent neural network; Estimator; Maximum likelihood sequence estimation; Maximum likelihood; Speech recognition; Bit error rate; Artificial intelligence; Interference (communication); Algorithm; Artificial neural network; Pattern recognition (psychology); Estimation theory; Telecommunications; Mathematics; Statistics; Decoding methods; Channel (broadcasting)","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":[0.00004898851,0.0001438646,0.0001726329,0.0000552616,0.00001854854,0.00003150768,0.0001944165,0.0001000035,0.00004891867],"category_scores_gemma":[0.00007949588,0.0001292147,0.0000300322,0.0003796205,0.00003465565,0.0001447879,0.0001044297,0.0003957504,0.00007937046],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003139256,"about_ca_system_score_gemma":0.000002918665,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":4.721838e-7,"about_ca_topic_score_gemma":0.000001654155,"domain_scores_codex":[0.9991584,0.00000719017,0.0002032574,0.0001708275,0.0001034858,0.0003568039],"domain_scores_gemma":[0.9997085,0.00005087213,0.000007755109,0.0001300066,0.000009643264,0.00009319895],"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":[0.00005741383,0.00007017174,0.02584,0.0002760261,0.00003450529,0.00006711931,0.0003948033,0.6346906,0.00169174,0.00547652,0.002855594,0.3285455],"study_design_scores_gemma":[0.0001926061,0.00009628311,0.009328619,0.00002926098,0.000003012618,0.000002461341,0.00003153357,0.9881436,0.0008268649,0.00001058643,0.001161862,0.0001733225],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9901004,0.0001884193,0.0008076602,0.002242058,0.0002545194,0.0001341404,5.383183e-7,0.001316159,0.00495608],"genre_scores_gemma":[0.9957572,0.00013486,0.003796195,0.0001839152,0.00008281638,0.00001284956,0.000002422792,0.00002160506,0.000008111932],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.353453,"threshold_uncertainty_score":0.5269223,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02092948129276943,"score_gpt":0.204192784416416,"score_spread":0.1832633031236466,"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."}}