Share Email Print
cover

Proceedings Paper

A new approach for neural network training and evaluation with applications to sensing systems
Author(s): Xinjia Chen; Ernest Walker
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Artificial neural networks are widely used in pattern recognition for sensing systems and other areas. In this paper, we propose to improve the performance of neural networks from the perspectives of output encoding rules, determination of training sample sizes, training performance index and evaluation of generalization error. We propose a new output encoding rule which significantly reduces the training error as compared to classical output encoding methods. Moreover, we develop a new training performance index which is closely relate to the generalization error and is a smooth function suitable for optimization by virtue of nonlinear programming. Furthermore, motivated by the crucial impact of training sample size on the generalization error and the computational complexity of training, we propose a rigorous method for determining appropriate number of training samples. Since the development of a neural network requires many cycles of training and performance evaluation, we introduce adaptive methods for estimating the generalization error. The new techniques of neural network training and evaluation have potential to improve the power of modern sensing systems.

Paper Details

Date Published: 4 June 2011
PDF: 12 pages
Proc. SPIE 8058, Independent Component Analyses, Wavelets, Neural Networks, Biosystems, and Nanoengineering IX, 80580K (4 June 2011); doi: 10.1117/12.883630
Show Author Affiliations
Xinjia Chen, Southern Univ. at Baton Rouge (United States)
Ernest Walker, Southern Univ. at Baton Rouge (United States)


Published in SPIE Proceedings Vol. 8058:
Independent Component Analyses, Wavelets, Neural Networks, Biosystems, and Nanoengineering IX
Harold Szu, Editor(s)

© SPIE. Terms of Use
Back to Top