{"id":"W4387350718","doi":"10.1109/tap.2023.3318830","title":"Autoencoder-Augmented Machine-Learning-Based Uncertainty Quantification for Electromagnetic Imaging","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Antennas and Propagation","topic":"Microwave Imaging and Scattering Analysis","field":"Engineering","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Autoencoder; Computer science; Artificial intelligence; Convolutional neural network; Iterative reconstruction; Machine learning; Uncertainty quantification; Dropout (neural networks); Artificial neural network; Inverse problem; Bayesian probability; Deep learning; Bayesian inference; Inference; Monte Carlo method; Image quality; Pattern recognition (psychology); Image (mathematics); Mathematics; Statistics","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":[0.0002126709,0.0001456349,0.0001280095,0.0002968488,0.0002547151,0.0000807203,0.0000524493,0.00003605291,0.00001868562],"category_scores_gemma":[0.000006981917,0.000145265,0.00007784011,0.0003915416,0.00003136132,0.00007400945,3.370717e-7,0.0001538483,0.00002373415],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004369363,"about_ca_system_score_gemma":0.00001314173,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004706382,"about_ca_topic_score_gemma":0.00004004424,"domain_scores_codex":[0.9992193,0.00003830428,0.000196183,0.0002236843,0.0001016626,0.0002208389],"domain_scores_gemma":[0.9996657,0.00006823902,0.00003362975,0.0001278848,0.00005535048,0.00004918189],"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":[0.00003682745,0.00002721705,0.00004937036,0.0001324631,0.00003965366,0.000001304857,0.0001407937,0.6990523,0.2619576,0.000007664655,0.0002074224,0.03834734],"study_design_scores_gemma":[0.000354861,0.00006675838,0.0001963751,0.00004159962,0.00005525152,0.000003450572,0.00004601769,0.963659,0.03486948,0.00003789649,0.0005105863,0.0001587554],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05585082,0.00008913098,0.9420677,0.0007429068,0.0001754582,0.0002248185,0.00002532746,0.0007952901,0.00002853776],"genre_scores_gemma":[0.9987085,0.0001243375,0.0005238727,0.00005580657,0.00001812119,0.00010034,0.000102031,0.00003424365,0.0003327368],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9428577,"threshold_uncertainty_score":0.5923736,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01244341863997639,"score_gpt":0.2279812054750227,"score_spread":0.2155377868350463,"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."}}