Share Email Print

Proceedings Paper

Hybrid location-content addressable memory: sensitivity analysis
Author(s): Seung K. Ahn; Seok B. Koh; Bo H. Wang
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Hybrid Location-Content Addressable Memory (HyLCAM), which has been recently proposed by the present authors, is a new class of neural networks which guarantees learning with a fast learning speed. In this paper, we present the sensitivity analysis of the HyLCAM to weight errors and input errors. The weight sensitivity specifies implementation requirements of the network; the input sensitivity characterizes the rejection capability of the HyLCAM. The rejection capability for unknown patterns is one of the most unique features of the HyLCAM and thus it is important to study the probability of rejection. For the illustration purpose, we solve a simple character recognition problem concerning with the performance of the HyLCAM in terms of learning and sensitivity.

Paper Details

Date Published: 19 August 1993
PDF: 8 pages
Proc. SPIE 1966, Science of Artificial Neural Networks II, (19 August 1993); doi: 10.1117/12.152611
Show Author Affiliations
Seung K. Ahn, GoldStar Central Research Lab. (South Korea)
Seok B. Koh, GoldStar Central Research Lab. (South Korea)
Bo H. Wang, GoldStar Central Research Lab. (South Korea)

Published in SPIE Proceedings Vol. 1966:
Science of Artificial Neural Networks II
Dennis W. Ruck, Editor(s)

© SPIE. Terms of Use
Back to Top