# Retrospective Uncertainties for Deep Models using Vine Copulas

## TL;DR

This paper introduces Vine-Copula Neural Networks (VCNN), a method that enhances deep models with reliable uncertainty estimates using vine copulas, applicable across various architectures and tasks, without modifying the original network.

## Contribution

The paper presents a novel post-hoc approach to uncertainty estimation in deep models using vine copulas, independent of network architecture or task type.

## Key findings

- VCNN provides well-calibrated uncertainty estimates.
- VCNN performs comparably to state-of-the-art methods.
- Applicable to diverse architectures and tasks.

## Abstract

Despite the major progress of deep models as learning machines, uncertainty estimation remains a major challenge. Existing solutions rely on modified loss functions or architectural changes. We propose to compensate for the lack of built-in uncertainty estimates by supplementing any network, retrospectively, with a subsequent vine copula model, in an overall compound we call Vine-Copula Neural Network (VCNN). Through synthetic and real-data experiments, we show that VCNNs could be task (regression/classification) and architecture (recurrent, fully connected) agnostic while providing reliable and better-calibrated uncertainty estimates, comparable to state-of-the-art built-in uncertainty solutions.