English

Uncertainty Propagation in Deep Neural Networks Using Extended Kalman Filtering

Machine Learning 2018-09-18 v1 Numerical Analysis Machine Learning

Abstract

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.

Keywords

Cite

@article{arxiv.1809.06009,
  title  = {Uncertainty Propagation in Deep Neural Networks Using Extended Kalman Filtering},
  author = {Jessica S. Titensky and Hayden Jananthan and Jeremy Kepner},
  journal= {arXiv preprint arXiv:1809.06009},
  year   = {2018}
}

Comments

4 Pages, 8 figures. Accepted at MIT IEEE Undergraduate Research Technology Conference 2018. Publication pending

R2 v1 2026-06-23T04:08:14.381Z