Prediction Limit Estimation for Neural Network Models

Abstract—A novel method for estimation of prediction limits for global and local approximating neural networks is presented. The method partitions the input space using self-organizing feature maps to introduce the concept of local neighborhoods, and calculates limits that indicate the extent to which one can rely on predictions for making future decisions. Index Terms—Estimation, feedforward neural networks, pre-diction intervals, prediction limits, self-organizing feature maps. I