{"id":"W3090189500","doi":"10.1007/s11082-020-02565-5","title":"Nonlinearity mitigation with a perturbation based neural network receiver","year":2020,"lang":"en","type":"article","venue":"Optical and Quantum Electronics","topic":"Optical Network Technologies","field":"Engineering","cited_by":21,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Artificial neural network; Nonlinear system; Computer science; Trimming; Quadrature amplitude modulation; Algorithm; Control theory (sociology); Physics; Artificial intelligence; 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":[0.00004932573,0.0001393677,0.0001511998,0.00001325438,0.00005904178,0.00004152333,0.0000733391,0.0001173453,0.00001151114],"category_scores_gemma":[0.00005011409,0.0001131548,0.0000242024,0.0002490752,0.00008382376,0.00009134186,0.00001807401,0.0003816661,0.000007775868],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000309619,"about_ca_system_score_gemma":0.00001872693,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":4.536269e-7,"about_ca_topic_score_gemma":0.000005161443,"domain_scores_codex":[0.9991985,0.00001207128,0.000127004,0.000181173,0.0001184833,0.0003627856],"domain_scores_gemma":[0.9996662,0.00009202059,0.00001333807,0.00009287407,0.00002946052,0.0001061788],"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":[0.0003479057,0.00007506987,0.001826831,0.0002101387,0.00009921678,0.00002953202,0.00008849689,0.5591223,0.002039609,0.3922491,0.00184294,0.04206892],"study_design_scores_gemma":[0.0002601683,0.0004416332,0.0004734269,0.00001280495,0.00002328377,0.000003574071,0.000008173001,0.9938709,0.0004720886,0.002099122,0.002169244,0.0001656129],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9624624,0.00132576,0.02853696,0.005733833,0.00005315868,0.0001948683,0.000002863115,0.000888283,0.0008018999],"genre_scores_gemma":[0.9834743,0.0001603299,0.01582031,0.000362233,0.000127534,0.000009238748,0.00001782231,0.00002298764,0.000005312888],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4347486,"threshold_uncertainty_score":0.461432,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007662919954252096,"score_gpt":0.1822588354309392,"score_spread":0.1745959154766872,"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."}}