Interval Neural Networks: Uncertainty Scores

03/25/2020
by   Luis Oala, et al.
9

We propose a fast, non-Bayesian method for producing uncertainty scores in the output of pre-trained deep neural networks (DNNs) using a data-driven interval propagating network. This interval neural network (INN) has interval valued parameters and propagates its input using interval arithmetic. The INN produces sensible lower and upper bounds encompassing the ground truth. We provide theoretical justification for the validity of these bounds. Furthermore, its asymmetric uncertainty scores offer additional, directional information beyond what Gaussian-based, symmetric variance estimation can provide. We find that noise in the data is adequately captured by the intervals produced with our method. In numerical experiments on an image reconstruction task, we demonstrate the practical utility of INNs as a proxy for the prediction error in comparison to two state-of-the-art uncertainty quantification methods. In summary, INNs produce fast, theoretically justified uncertainty scores for DNNs that are easy to interpret, come with added information and pose as improved error proxies - features that may prove useful in advancing the usability of DNNs especially in sensitive applications such as health care.

READ FULL TEXT

page 11

page 22

page 23

page 24

research
08/05/2021

PI3NN: Prediction intervals from three independently trained neural networks

We propose a novel prediction interval method to learn prediction mean v...
research
05/13/2021

Interval Deep Learning for Uncertainty Quantification in Safety Applications

Deep neural networks (DNNs) are becoming more prevalent in important saf...
research
10/31/2022

Confidence-Nets: A Step Towards better Prediction Intervals for regression Neural Networks on small datasets

The recent decade has seen an enormous rise in the popularity of deep le...
research
03/27/2020

Interval Neural Networks as Instability Detectors for Image Reconstructions

This work investigates the detection of instabilities that may occur whe...
research
05/23/2023

Uncertainty Quantification over Graph with Conformalized Graph Neural Networks

Graph Neural Networks (GNNs) are powerful machine learning prediction mo...
research
07/23/2020

DeepKriging: Spatially Dependent Deep Neural Networks for Spatial Prediction

In spatial statistics, a common objective is to predict the values of a ...
research
06/03/2019

Correctness Verification of Neural Networks

We present the first verification that a neural network produces a corre...

Please sign up or login with your details

Forgot password? Click here to reset