A new approach for neural network training and evaluation with applications to sensing systems

Xinjia Chen; Ernest Walker

doi:10.1117/12.883630

3 June 2011 A new approach for neural network training and evaluation with applications to sensing systems

Xinjia Chen, Ernest Walker

Proceedings Volume 8058, Independent Component Analyses, Wavelets, Neural Networks, Biosystems, and Nanoengineering IX; 80580K (2011) https://doi.org/10.1117/12.883630
Event: SPIE Defense, Security, and Sensing, 2011, Orlando, Florida, United States

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.

Citation Download Citation

Xinjia Chen and Ernest Walker "A new approach for neural network training and evaluation with applications to sensing systems", Proc. SPIE 8058, Independent Component Analyses, Wavelets, Neural Networks, Biosystems, and Nanoengineering IX, 80580K (3 June 2011); https://doi.org/10.1117/12.883630

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available