Selection of training samples for learning with hints

Training with hints is a powerful method for incorporating almost any type of prior knowledge into neural network models. In this paper we demonstrate how the hints can be constructed from numerical approximation of the regularization cost function, and discuss the problem of selecting the hint samp...

Full description

Saved in:
Bibliographic Details
Main Authors: Lampinen, J., Litkey, P., Hakkarainen, H.
Format: Conference Proceeding
Language:English
Subjects:
Computer networks
Cost function
Fuzzy sets
Knowledge engineering
Laboratories
Neural networks
Nonlinear distortion
Power engineering and energy
Power engineering computing
Testing
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Training with hints is a powerful method for incorporating almost any type of prior knowledge into neural network models. In this paper we demonstrate how the hints can be constructed from numerical approximation of the regularization cost function, and discuss the problem of selecting the hint samples. We give a simple algorithm for placing the hint samples in such regions in the input space where the hint error is large, and for selecting the minimum sufficient set of hint samples by removing the correlated samples.
ISSN:1098-7576
1558-3902
DOI:10.1109/IJCNN.1999.831176