Volume 14, Number 4

Uncertainty Estimation in Neural Networks Through Multi-Task Learning

  Authors

Ashish James and Anusha James, Insitute for Infocomm Research (I2R), Singapore

  Abstract

The impressive predictive performance of deep learning techniques on a wide range of tasks has led to its widespread use. Estimating the confidence of these predictions is paramount for improving the safety and reliability of such systems. However, the uncertainty estimates provided by neural networks (NNs) tend to be overconfident and unreasonable. Previous studies have found out that ensemble of NNs typically produce good predictions and uncertainty estimates. Inspired by these, this paper presents a new framework that can quantitatively estimate the uncertainties by leveraging the advances in multi-task learning through slight modification to the existing training pipelines. This promising algorithm is developed with an intention of deployment in real world problems which already boast a good predictive performance by reusing those pretrained models. The idea is to capture the behavior of the trained NNs for the base task by augmenting it with the uncertainty estimates from a supplementary network. A series of experiments show that the proposed approach produces well calibrated uncertainty estimates with high quality predictions.

  Keywords

Uncertainty estimation, Neural Networks, Multi-task Learning, Regression.