Unified Uncertainties: Combining Input, Data and Model Uncertainty into a Single Formulation

TL;DR

This paper introduces a unified approach to model and propagate input, data, and model uncertainties within neural networks, enhancing prediction stability and providing a comprehensive uncertainty estimation framework.

Contribution

It presents a novel method for propagating input uncertainty through neural networks, integrating multiple uncertainty types into a single formulation.

Findings

Propagation of input uncertainty improves decision boundary stability.

Input uncertainty propagation induces model uncertainty at outputs.

Explicit input uncertainty incorporation benefits scenarios with known input noise.

Abstract

Modelling uncertainty in Machine Learning models is essential for achieving safe and reliable predictions. Most research on uncertainty focuses on output uncertainty (predictions), but minimal attention is paid to uncertainty at inputs. We propose a method for propagating uncertainty in the inputs through a Neural Network that is simultaneously able to estimate input, data, and model uncertainty. Our results show that this propagation of input uncertainty results in a more stable decision boundary even under large amounts of input noise than comparatively simple Monte Carlo sampling. Additionally, we discuss and demonstrate that input uncertainty, when propagated through the model, results in model uncertainty at the outputs. The explicit incorporation of input uncertainty may be beneficial in situations where the amount of input uncertainty is known, though good datasets for this are still needed.