Share Email Print

Proceedings Paper

Hetero-association for pattern translation
Author(s): Francis T. S. Yu; Thomas Taiwei Lu; Xiangyang Yang
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

A hetero-association neural network using an interpattern association algorithm is presented. By using simple logical rules, hetero-association memory can be constructed based on the association between the input-output reference patterns. For optical implementation, a compact size liquid crystal television neural network is used. Translations between the English letters and the Chinese characters as well as Arabic and Chinese numerics are demonstrated. The authors have shown that the hetero-association model can perform more effectively in comparison to the Hopfield model in retrieving large numbers of similar patterns.

Paper Details

Date Published: 1 September 1991
PDF: 12 pages
Proc. SPIE 1507, Holographic Optics III: Principles and Applications, (1 September 1991); doi: 10.1117/12.47044
Show Author Affiliations
Francis T. S. Yu, The Pennsylvania State Univ. (United States)
Thomas Taiwei Lu, Photonics Research (United States)
Xiangyang Yang, The Pennsylvania State Univ. (United States)

Published in SPIE Proceedings Vol. 1507:
Holographic Optics III: Principles and Applications
G. Michael Morris, Editor(s)

© SPIE. Terms of Use
Back to Top