Optimal Uncertainty-guided Neural Network Training

TL;DR

This paper introduces a customizable smooth cost function for neural networks to generate optimal prediction intervals, improving convergence and consistency in uncertainty quantification for wind power and electricity demand data.

Contribution

It proposes a novel, highly customizable cost function that enhances convergence and quality of prediction intervals in neural network-based uncertainty quantification.

Findings

Improves convergence probability from 99.2% to 99.8%.

Reduces variation in prediction interval quality.

Accelerates neural network training.

Abstract

The neural network (NN)-based direct uncertainty quantification (UQ) methods have achieved the state of the art performance since the first inauguration, known as the lower-upper-bound estimation (LUBE) method. However, currently-available cost functions for uncertainty guided NN training are not always converging and all converged NNs are not generating optimized prediction intervals (PIs). Moreover, several groups have proposed different quality criteria for PIs. These raise a question about their relative effectiveness. Most of the existing cost functions of uncertainty guided NN training are not customizable and the convergence of training is uncertain. Therefore, in this paper, we propose a highly customizable smooth cost function for developing NNs to construct optimal PIs. The optimized average width of PIs, PI-failure distances and the PI coverage probability (PICP) are computed for the test dataset. The performance of the proposed method is examined for the wind power generation and the electricity demand data. Results show that the proposed method reduces variation in the quality of PIs, accelerates the training, and improves convergence probability from 99.2% to 99.8%.