Variational Neural Networks

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaperConference articleResearchpeer-review

Abstract

Bayesian Neural Networks provide a tool to estimate the uncertainty of a neural network by considering a distribution over weights and sampling different models for each input. In this paper, we propose a method for uncertainty estimation in neural networks which, instead of considering a distribution over weights, samples outputs of each layer from a corresponding Gaussian distribution, parametrized by the predictions of mean and variance sub-layers. In uncertainty quality estimation experiments, we show that the proposed method achieves better uncertainty quality than other single-bin Bayesian Model Averaging methods, such as Monte Carlo Dropout or Bayes By Backpropagation methods.
Original languageEnglish
JournalProcedia Computer Science
Volume222
Pages (from-to)104-113
Number of pages10
ISSN1877-0509
DOIs
Publication statusPublished - 2023

Keywords

  • Bayesian Deep Learning
  • Bayesian Neural Networks
  • Uncertainty Estimation

Fingerprint

Dive into the research topics of 'Variational Neural Networks'. Together they form a unique fingerprint.

Cite this