Share Email Print
cover

Proceedings Paper

Classification properties and classification mechanisms of feed-forward neural network classifiers
Author(s): De-Shuang Huang
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

This paper studies the classification properties and classification mechanisms of outer-supervised feed-forward neural network classifiers (FNNC). It is shown that nonlinear FNNCs can break through the 'bottleneck' behaviors for linear FNNCs. Assume that the involved FNNCs are classifiers that associate only one output node with each class, after the global minimum solutions with null costs based on batch-style learning are obtained, it is shown that in the case of the linear output network classifiers, the class weight vectors corresponding to different output nodes are orthogonal, and in the case of sigmoid output activation functions, the jth class weight vector must be situated in the negative direction of the i(i does not equal j) th class weight vector.

Paper Details

Date Published: 12 March 1999
PDF: 5 pages
Proc. SPIE 3719, Sensor Fusion: Architectures, Algorithms, and Applications III, (12 March 1999); doi: 10.1117/12.341368
Show Author Affiliations
De-Shuang Huang, Beijing Institute of Systems Engineering (China)


Published in SPIE Proceedings Vol. 3719:
Sensor Fusion: Architectures, Algorithms, and Applications III
Belur V. Dasarathy, Editor(s)

© SPIE. Terms of Use
Back to Top