Picture for Jessica S. Titensky

Jessica S. Titensky

Uncertainty Propagation in Deep Neural Networks Using Extended Kalman Filtering

Add code
Sep 17, 2018
Jessica S. Titensky, Hayden Jananthan, Jeremy Kepner
Figure 1 for Uncertainty Propagation in Deep Neural Networks Using Extended Kalman Filtering
Figure 2 for Uncertainty Propagation in Deep Neural Networks Using Extended Kalman Filtering
Figure 3 for Uncertainty Propagation in Deep Neural Networks Using Extended Kalman Filtering
Figure 4 for 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.

* 4 Pages, 8 figures. Accepted at MIT IEEE Undergraduate Research Technology Conference 2018. Publication pending 
Viaarxiv icon
Github IconAccess Paper or Ask Questions
Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon