DeepAI AI Chat
Log In Sign Up

Confident Neural Network Regression with Bootstrapped Deep Ensembles

by   Laurens Sluijterman, et al.

With the rise of the popularity and usage of neural networks, trustworthy uncertainty estimation is becoming increasingly essential. In this paper we present a computationally cheap extension of Deep Ensembles for a regression setting called Bootstrapped Deep Ensembles that explicitly takes the effect of finite data into account using a modified version of the parametric bootstrap. We demonstrate through a simulation study that our method has comparable or better prediction intervals and superior confidence intervals compared to Deep Ensembles and other state-of-the-art methods. As an added bonus, our method is better capable of detecting overfitting than standard Deep Ensembles.


page 1

page 2

page 3

page 4


Layer Ensembles

Deep Ensembles, as a type of Bayesian Neural Networks, can be used to es...

Prediction intervals for Deep Neural Networks

The aim of this paper is to propose a suitable method for constructing p...

Fixed-time descriptive statistics underestimate extremes of epidemic curve ensembles

Across the world, scholars are racing to predict the spread of the novel...

Deep Sub-Ensembles for Fast Uncertainty Estimation in Image Classification

Fast estimates of model uncertainty are required for many robust robotic...

Prediction Intervals: Split Normal Mixture from Quality-Driven Deep Ensembles

Prediction intervals are a machine- and human-interpretable way to repre...

Multi-Model Ensemble Optimization

Methodology and optimization algorithms for sparse regression are extend...