Overtraining in back-propagation neural networks: A CRT color calibration example

✍ Scribed by David H. Alman; Liao Ningfang

• Book ID: 102115371
• Publisher: John Wiley and Sons
• Year: 2002
• Tongue: English
• Weight: 69 KB
• Volume: 27
• Category: Article
• ISSN: 0361-2317
• DOI: 10.1002/col.10027

✦ Synopsis

Abstract

A condition of overtraining a back‐propagation neural network exists when excessive model degrees of freedom are used in network training. A CRT color calibration experiment was done to illustrate methods to avoid an overtrained condition in model development. Cross‐validation, in which the experimental data are split into parameter‐training and independent‐test data sets, is advocated. © 2002 Wiley Periodicals, Inc. Col Res Appl, 27, 122–125, 2002; DOI 10.1002/col.10027