Share Email Print
cover

Proceedings Paper

Ultrafast learning in a hard-limited neural network pattern recognizer
Author(s): Chia-Lun John Hu
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

As we published in the last five years, the supervised learning in a hard-limited perceptron system can be accomplished in a noniterative manner if the input-output mapping to be learned satisfies a certain positive-linear-independency (or PLI) condition. When this condition is satisfied (for most practical pattern recognition applications, this condition should be satisfied,) the connection matrix required to meet this mapping can be obtained noniteratively in one step. Generally, there exist infinitively many solutions for the connection matrix when the PLI condition is satisfied. We can then select an optimum solution such that the recognition of any untrained patterns will become optimally robust in the recognition mode. The learning speed is very fast and close to real-time because the learning process is noniterative and one-step. This paper reports the theoretical analysis and the design of a practical charter recognition system for recognizing hand-written alphabets. The experimental result is recorded in real-time on an unedited video tape for demonstration purposes. It is seen from this real-time movie that the recognition of the untrained hand-written alphabets is invariant to size, location, orientation, and writing sequence, even the training is done with standard size, standard orientation, central location and standard writing sequence.

Paper Details

Date Published: 4 March 1996
PDF: 4 pages
Proc. SPIE 2664, Applications of Artificial Neural Networks in Image Processing, (4 March 1996); doi: 10.1117/12.234257
Show Author Affiliations
Chia-Lun John Hu, Southern Illinois Univ./Carbondale (United States)


Published in SPIE Proceedings Vol. 2664:
Applications of Artificial Neural Networks in Image Processing
Nasser M. Nasrabadi; Aggelos K. Katsaggelos, Editor(s)

© SPIE. Terms of Use
Back to Top