{"id":"W2915945464","doi":"10.1109/tim.2019.2895495","title":"Deep-Learning-Based Neural Network Training for State Estimation Enhancement: Application to Attitude Estimation","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Instrumentation and Measurement","topic":"Target Tracking and Data Fusion in Sensor Networks","field":"Computer Science","cited_by":111,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Khalifa University of Science, Technology and Research","keywords":"Overfitting; Computer science; Artificial intelligence; Artificial neural network; Estimator; Noise (video); Kalman filter; Inertial measurement unit; Deep learning; Dropout (neural networks); Noise measurement; Machine learning; Stability (learning theory); Noise reduction","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":[0.0005655333,0.0001906307,0.0001644281,0.0001496681,0.0003824983,0.0001902442,0.000176783,0.00005389468,0.00002256327],"category_scores_gemma":[0.00000904137,0.000201217,0.00005778987,0.0003059202,0.00001628048,0.0004004661,0.00000264096,0.0001450704,0.00004653723],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001564027,"about_ca_system_score_gemma":0.00004563481,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001467516,"about_ca_topic_score_gemma":0.00003495803,"domain_scores_codex":[0.9982388,0.00008042856,0.0003696837,0.0004815765,0.0005319901,0.0002974994],"domain_scores_gemma":[0.9991937,0.00008504985,0.0001524823,0.0002777474,0.0001563673,0.0001346345],"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":[0.00005130347,0.00004140769,0.00001924185,0.00002065607,0.00001180513,6.532154e-8,0.0003801922,0.6036905,0.0008847115,0.0001521609,0.00002489789,0.3947231],"study_design_scores_gemma":[0.001127523,0.000407976,0.0004663733,0.00007315918,0.00002058144,0.000001579289,0.0000526849,0.9894132,0.007203747,0.0002324603,0.0007880582,0.000212652],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01806399,0.00001578386,0.9790956,0.0004934163,0.0008644194,0.001230417,0.000005071633,0.0001856258,0.00004563974],"genre_scores_gemma":[0.8686985,0.000008589858,0.1302203,0.0005913562,0.00002206048,0.0003706895,0.00003212712,0.0000150813,0.00004134474],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8506345,"threshold_uncertainty_score":0.820539,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02971224321442426,"score_gpt":0.2686895848397728,"score_spread":0.2389773416253486,"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."}}