Share Email Print
cover

Proceedings Paper

Training Of A Neural Network For Object Recognition Using Error Backpropagation
Author(s): Antonio Miguel de Campos; Margarida Machado
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

In the work presented in this paper, graphical representations showing the typical evolution of the mapping function of the various neurons in a three-layered feed-forward network, are used to help gaining the necessary insight to error backpropagation training. The study of the learning behaviour of a simple object classifier is presented, and commented.

Paper Details

Date Published: 1 February 1990
PDF: 12 pages
Proc. SPIE 1197, Automated Inspection and High-Speed Vision Architectures III, (1 February 1990); doi: 10.1117/12.969959
Show Author Affiliations
Antonio Miguel de Campos, LNETI - Ministry of Industry and Energy (Portugal)
Margarida Machado, LNETI - Ministry of Industry and Energy (Portugal)


Published in SPIE Proceedings Vol. 1197:
Automated Inspection and High-Speed Vision Architectures III
Michael J. W. Chen, Editor(s)

© SPIE. Terms of Use
Back to Top