# Depth Uncertainty in Neural Networks

Source: [Depth Uncertainty in Neural Networks](<https://www.sota2.com/research/paper/68fa68df1e209131cea1edb9>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T22:47:52.778Z

Authors: Javier Antor\\'an, James Urquhart Allingham, Jos\\'e Miguel Hern\\'andez-Lobato

Published: 2020-06-15T14:33:40.000Z

## Abstract

Existing methods for estimating uncertainty in deep learning tend to require multiple forward passes, making them unsuitable for applications where computational resources are limited. To solve this, we perform probabilistic reasoning over the depth of neural networks. Different depths correspond to subnetworks which share weights and whose predictions are combined via marginalisation, yielding model uncertainty. By exploiting the sequential structure of feed-forward networks, we are able to both evaluate our training objective and make predictions with a single forward pass. We validate our approach on real-world regression and image classification tasks. Our approach provides uncertainty calibration, robustness to dataset shift, and accuracies competitive with more computationally expensive baselines.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2006.08437>)

[PDF](<https://arxiv.org/pdf/2006.08437.pdf>)