Share Email Print

Proceedings Paper

Neural network training algorithm that can predict generalization capacity
Author(s): Jin Lu; Wenli Xu; Zengjin Han
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Neural network training requires a large quantity of samples and consumes a great deal of computing time. Despite this, we still do not know the generalization capacity of a trained neural network in a certain domain. In this paper, we propose an algorithm for training neural networks to approximate polynomials. This algorithm can work with a relatively small sample set and predict the generalization capacity of the learned neural network. Simulation results demonstrate the property of this algorithm.

Paper Details

Date Published: 28 August 1995
PDF: 6 pages
Proc. SPIE 2620, International Conference on Intelligent Manufacturing, (28 August 1995); doi: 10.1117/12.217526
Show Author Affiliations
Jin Lu, Tsinghua Univ. (China)
Wenli Xu, Tsinghua Univ. (China)
Zengjin Han, Tsinghua Univ. (China)

Published in SPIE Proceedings Vol. 2620:
International Conference on Intelligent Manufacturing
Shuzi Yang; Ji Zhou; Cheng-Gang Li, Editor(s)

© SPIE. Terms of Use
Back to Top