{"id":"W4384558730","doi":"10.1364/oe.493240","title":"Neural network architectures for optical channel nonlinear compensation in digital subcarrier multiplexing systems","year":2023,"lang":"en","type":"article","venue":"Optics Express","topic":"Optical Network Technologies","field":"Engineering","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Huawei Technologies (Canada)","funders":"","keywords":"Subcarrier; Computer science; Subcarrier multiplexing; Electronic engineering; Multiplexing; Transmission (telecommunications); Artificial neural network; Nonlinear system; Wavelength-division multiplexing; Equalization (audio); Interference (communication); Compensation (psychology); Nonlinear distortion; Orthogonal frequency-division multiplexing; Channel (broadcasting); Optics; Telecommunications; Artificial intelligence; Engineering; Physics; Bandwidth (computing)","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":[0.0001491773,0.0002174885,0.0002911068,0.0001401187,0.0000630072,0.0001682157,0.0002588271,0.0001937879,0.000001119694],"category_scores_gemma":[0.0002013139,0.0002184856,0.00006934376,0.0004017109,0.000079285,0.00007872396,0.0001216248,0.0002890995,0.00001575265],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004483967,"about_ca_system_score_gemma":0.00000578039,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002175248,"about_ca_topic_score_gemma":0.00000495737,"domain_scores_codex":[0.9985784,0.00000759362,0.0003383943,0.0002456194,0.0001750029,0.0006549837],"domain_scores_gemma":[0.9990733,0.0005043453,0.00002733105,0.0002733264,0.00004442077,0.00007725899],"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":[0.00001900128,0.00001051124,0.0003622431,0.00009281896,0.0000174756,0.00001367136,0.0000800125,0.9949337,0.0002884231,0.00273073,0.0002490935,0.001202342],"study_design_scores_gemma":[0.0003665402,0.00004020725,0.000323111,0.00006816397,0.000005762231,0.000004203679,0.0001386498,0.9970191,0.0002444141,0.001123479,0.0004198255,0.0002465698],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9815952,0.0001374108,0.01399156,0.00008341847,0.0009612978,0.0007091982,0.00007668167,0.001684331,0.0007609379],"genre_scores_gemma":[0.9866641,0.00001328136,0.01243469,0.000008075636,0.000518318,0.0001579571,0.00009496107,0.00007466447,0.00003392833],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005068961,"threshold_uncertainty_score":0.8909584,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02107305031785716,"score_gpt":0.2377241196909035,"score_spread":0.2166510693730463,"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."}}