{"id":"W4226476934","doi":"10.1364/ofc.2022.w2a.35","title":"Perturbation-aided deep neural network for dual-polarization optical communication systems","year":2022,"lang":"en","type":"article","venue":"Optical Fiber Communication Conference (OFC) 2022","topic":"Optical Network Technologies","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Huawei Technologies (Canada); University of British Columbia; Memorial University of Newfoundland","funders":"","keywords":"Artificial neural network; Computer science; Perturbation (astronomy); Multiplexing; Nonlinear system; Polarization (electrochemistry); Optical communication; Communications system; Neural system; Electronic engineering; Physics; Optics; Artificial intelligence; Telecommunications; Neuroscience; Engineering; Chemistry","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003326116,0.0005336367,0.0003020603,0.0001892702,0.000268577,0.0003489784,0.0007454779,0.0006504677,0.001319736],"category_scores_gemma":[0.0005892192,0.000252559,0.0002569212,0.0002642154,0.0004569937,0.0007910757,0.0009274057,0.001182609,0.0003457046],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004580037,"about_ca_system_score_gemma":0.0005929043,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00161227,"about_ca_topic_score_gemma":0.00248408,"domain_scores_codex":[0.9998092,0.00004156979,0.000006998378,0.00002886334,0.00008299845,0.00003039449],"domain_scores_gemma":[0.9998657,0.00004295498,0.0000209258,0.00001642113,0.00004229718,0.00001171369],"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":[0.0003050618,0.0001521598,0.000865842,0.0001205533,0.00008575368,0.0001781537,0.00007497909,0.6518319,0.1036615,0.02370491,0.003214259,0.2158049],"study_design_scores_gemma":[0.000001951551,0.00001685363,0.00003338732,0.000001489679,0.00000252601,0.00001161271,0.000001330867,0.9930933,0.005540907,0.001015063,0.0002785738,0.000003038215],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03178394,0.0003725153,0.9637166,0.0004000315,0.00006558758,0.00002635956,0.00005239351,0.0006262811,0.002956295],"genre_scores_gemma":[0.8005149,0.000396303,0.1922205,0.0002692279,0.00007231359,0.0000735801,0.0001291258,0.00006110584,0.00626293],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00161227,"threshold_uncertainty_score":0.004414976,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02301413190263681,"score_gpt":0.2357846408528581,"score_spread":0.2127705089502213,"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."}}