Dual Accuracy-Quality-Driven Neural Network for Prediction Interval Generation

by   Giorgio Morales, et al.

Accurate uncertainty quantification is necessary to enhance the reliability of deep learning models in real-world applications. In the case of regression tasks, prediction intervals (PIs) should be provided along with the deterministic predictions of deep learning models. Such PIs are useful or "high-quality” as long as they are sufficiently narrow and capture most of the probability density. In this paper, we present a method to learn prediction intervals for regression-based neural networks automatically in addition to the conventional target predictions. In particular, we train two companion neural networks: one that uses one output, the target estimate, and another that uses two outputs, the upper and lower bounds of the corresponding PI. Our main contribution is the design of a loss function for the PI-generation network that takes into account the output of the target-estimation network and has two optimization objectives: minimizing the mean prediction interval width and ensuring the PI integrity using constraints that maximize the prediction interval probability coverage implicitly. Both objectives are balanced within the loss function using a self-adaptive coefficient. Furthermore, we apply a Monte Carlo-based approach that evaluates the model uncertainty in the learned PIs. Experiments using a synthetic dataset, six benchmark datasets, and a real-world crop yield prediction dataset showed that our method was able to maintain a nominal probability coverage and produce narrower PIs without detriment to its target estimation accuracy when compared to those PIs generated by three state-of-the-art neural-network-based methods.


page 1

page 10


High-Quality Prediction Intervals for Deep Learning: A Distribution-Free, Ensembled Approach

Deep neural networks are a powerful technique for learning complex funct...

Accurate Prediction and Uncertainty Estimation using Decoupled Prediction Interval Networks

We propose a network architecture capable of reliably estimating uncerta...

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...

Tight Prediction Intervals Using Expanded Interval Minimization

Prediction intervals are a valuable way of quantifying uncertainty in re...

Learning Prediction Intervals for Regression: Generalization and Calibration

We study the generation of prediction intervals in regression for uncert...

Prediction intervals for neural network models using weighted asymmetric loss functions

We develop a novel and simple method to produce prediction intervals (PI...

Adaptive, Distribution-Free Prediction Intervals for Deep Neural Networks

This paper addresses the problem of assessing the variability of predict...

Please sign up or login with your details

Forgot password? Click here to reset