Prediction Intervals for Deep Learning Neural Networks

Prediction intervals provide a measure of uncertainty for predictions on regression problems.

For example, a 95% prediction interval indicates that 95 out of 100 times, the true value will fall between the lower and upper values of the range. This is different from a simple point prediction that might represent the center of the uncertainty interval.

There are no standard techniques for calculating a prediction interval for deep learning neural networks on regression predictive modeling problems. Nevertheless, a quick and dirty prediction interval can be estimated using an ensemble of models that, in turn, provide a distribution of point predictions from which an interval can be calculated.

In this tutorial, you will discover how to calculate a prediction interval

 

 

To finish reading, please visit source site