Uncertainty Propagation in Deep Neural Networks Using Extended Kalman Filtering
Extended Kalman Filtering (EKF) can be used to propagate and quantify input uncertainty through a Deep Neural Network (DNN) assuming mild hypotheses on the input distribution. This methodology yields results comparable to existing methods of uncertainty propagation for DNNs while lowering the computational overhead considerably. Additionally, EKF allows model error to be naturally incorporated into the output uncertainty.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Extending the practical applicability of the Kalman Filter
A Schmidt filter is a modification of the Kalman filter that allows to append system parameters as states and considers their uncertainty effect in the filtering process without attempting to estimate such parameters. Th…
Neural Aided Kalman Filtering for UAV State Estimation in Degraded Sensing Environments
Accurate state estimation of nonlinear dynamical systems is fundamental to modern aerospace operations across air, sea, and space domains. Online tracking of adversarial unmanned aerial vehicles (UAVs) is especially chal…
Filtered Neural Galerkin model reduction schemes for efficient propagation of initial condition uncertainties in digital twins
Uncertainty quantification in digital twins is critical to enable reliable and credible predictions beyond available data. A key challenge is that ensemble-based approaches can become prohibitively expensive when embedde…
Federated Data-Driven Kalman Filtering for State Estimation
This paper proposes a novel localization framework based on collaborative training or federated learning paradigm, for highly accurate localization of autonomous vehicles. More specifically, we build on the standard appr…
Autonomous DrivingAutonomous VehiclesDecision MakingFederated Learning+2A Look at Improving Robustness in Visual-inertial SLAM by Moment Matching
The fusion of camera sensor and inertial data is a leading method for ego-motion tracking in autonomous and smart devices. State estimation techniques that rely on non-linear filtering are a strong paradigm for solving t…
State Estimation