{"id":"W4387872867","doi":"10.23919/usnc-ursi54200.2023.10289297","title":"Deep-Learning Enabled Uncertainty Estimation Applied to Experimental Near-Field Microwave Imaging of 2-D Dielectric Cylinders","year":2023,"lang":"en","type":"article","venue":"","topic":"Microwave Imaging and Scattering Analysis","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"","keywords":"Microwave imaging; Dropout (neural networks); Dielectric; Microwave; Inference; Cylinder; Iterative reconstruction; Solver; Bayesian inference; Computer science; Finite element method; Deep learning; Artificial intelligence; Field (mathematics); Bayesian probability; Algorithm; Materials science; Machine learning; Mathematics; Physics; Geometry; Telecommunications","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":[0.000189753,0.0001745608,0.0002339387,0.0003073978,0.0001043192,0.00007358853,0.0001364946,0.00004095739,0.0001058645],"category_scores_gemma":[0.00004074777,0.0001845091,0.00008757797,0.0008959018,0.00001891926,0.000058193,0.00004817366,0.0001642296,0.0001487033],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008339719,"about_ca_system_score_gemma":0.00001110546,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001253728,"about_ca_topic_score_gemma":0.000009337834,"domain_scores_codex":[0.9989517,0.0000190828,0.0002787296,0.0002305266,0.0001559895,0.0003639411],"domain_scores_gemma":[0.9995674,0.00009217168,0.00003447035,0.0001921691,0.00002692503,0.00008679339],"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":[0.000007587674,0.000006994185,0.0002529297,0.00002629777,0.00003928813,0.000002511952,0.0009083376,0.6100965,0.3680145,0.00002042079,0.0007722711,0.01985241],"study_design_scores_gemma":[0.0001567082,0.00001388636,0.0001415512,0.00001542387,0.00001674931,0.000002246955,0.0008269316,0.7331041,0.2654229,0.00001958987,0.000118907,0.0001609456],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7392172,0.0001454586,0.2470747,0.0002060959,0.0001178603,0.0001662088,6.267208e-7,0.001020892,0.01205096],"genre_scores_gemma":[0.994563,0.00001065657,0.004994013,0.0001113526,0.00002272254,0.00002356036,0.00002012933,0.00003897323,0.0002156189],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2553458,"threshold_uncertainty_score":0.7524061,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006165274099695763,"score_gpt":0.2249042323222887,"score_spread":0.2187389582225929,"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."}}