Title :
Prediction limit estimation for neural network models
Author :
Chinman, R.B. ; Ding, J.
Author_Institution :
Ind. & Manuf. Eng. Dept., North Dakota State Univ., Fargo, ND, USA
fDate :
11/1/1998 12:00:00 AM
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
Keywords :
approximation theory; modelling; self-organising feature maps; global approximating neural networks; input space partitioning; local approximating neural networks; local neighborhoods; neural network models; prediction limit estimation; self-organizing feature maps; Computer networks; Digital arithmetic; Feedforward neural networks; Feedforward systems; Function approximation; Lattices; Neural networks; Neurons; Predictive models; Testing;
Journal_Title :
Neural Networks, IEEE Transactions on
