# Uncertainty Propagation in Deep Neural Networks Using Extended Kalman Filtering

arXiv: https://arxiv.org/abs/1809.06009 · HTML: https://mlsanity.com/paper/1809.06009/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Sep 2018.

## Built on by (most cited first, 8 of 8)

- [Propagation and Attribution of Uncertainty in Medical Imaging Pipelines](https://mlsanity.com/paper/2309.16831/) (2023)
- [A Trustworthy Framework for Medical Image Analysis with Deep Learning](https://mlsanity.com/paper/2212.02764/) (2022)
- [Assumed Density Filtering and Smoothing with Neural Network Surrogate Models](https://mlsanity.com/paper/2511.09016/) (2025)
- [Performance Bounds for Neural Network Estimators: Applications in Fault Detection](https://mlsanity.com/paper/2103.12141/) (2021)
- [Towards Trustworthy Healthcare AI: Attention-Based Feature Learning for COVID-19 Screening With Chest Radiography](https://mlsanity.com/paper/2207.09312/) (2022)
- [Uncertainty Propagation through Trained Deep Neural Networks Using Factor Graphs](https://mlsanity.com/paper/2312.05946/) (2023)
- [Uncertainty propagation through trained multi-layer perceptrons: Exact analytical results](https://mlsanity.com/paper/2601.16830/) (2026)
- [Uncertainty propagation in auto-regressive random neural network models](https://mlsanity.com/paper/2608.20483/) (2026)

## Abstract (arXiv)

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.