{"id":"W3177943438","doi":"10.1109/jstqe.2021.3096421","title":"BraggNet: Complex Photonic Integrated Circuit Reconstruction Using Deep Learning","year":2021,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Quantum Electronics","topic":"Neural Networks and Reservoir Computing","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Photonics; Fabrication; Inverse; Grating; Deep learning; Waveguide; Inverse problem; Algorithm; Artificial intelligence; Materials science; Optoelectronics; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0005038177,0.0002151053,0.0004432237,0.0002889884,0.0002062736,0.0002138702,0.0006525986,0.0001590265,0.00001863116],"category_scores_gemma":[0.0002021446,0.0002053969,0.0001366694,0.002207138,0.00003857032,0.0005122283,0.00007761789,0.001798125,0.000001345672],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004832577,"about_ca_system_score_gemma":0.000925347,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001653068,"about_ca_topic_score_gemma":0.0001094101,"domain_scores_codex":[0.9974002,0.0003959557,0.0008469055,0.0003203584,0.000378183,0.0006583845],"domain_scores_gemma":[0.9977847,0.0001524032,0.0006053133,0.0002441358,0.00110363,0.0001098379],"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":[0.00006536694,0.0003078523,0.006476006,0.00007913537,0.0002583964,0.001045025,0.000756875,0.3957223,0.2902287,0.01316037,0.0001137353,0.2917863],"study_design_scores_gemma":[0.0006267701,0.0002982086,0.0008327134,0.0001745155,0.00001710299,0.00408514,0.0000530873,0.9731644,0.01368078,0.00446906,0.002345826,0.0002524385],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7803004,0.003645668,0.2145496,0.0002673565,0.00104183,0.00006778206,1.661828e-7,0.00004483924,0.00008242123],"genre_scores_gemma":[0.9840363,0.001759034,0.01355932,0.0001342996,0.0004441379,6.755297e-7,0.000002184827,0.000022404,0.00004168086],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5774421,"threshold_uncertainty_score":0.8375844,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02913466826270724,"score_gpt":0.2582573104229395,"score_spread":0.2291226421602322,"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."}}