19 August 1993 Hybrid location-content addressable memory: sensitivity analysis
Author Affiliations +
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.
© (1993) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Seung K. Ahn, Seung K. Ahn, Seok B. Koh, Seok B. Koh, Bo H. Wang, Bo H. Wang, } "Hybrid location-content addressable memory: sensitivity analysis", Proc. SPIE 1966, Science of Artificial Neural Networks II, (19 August 1993); doi: 10.1117/12.152611; https://doi.org/10.1117/12.152611
PROCEEDINGS
8 PAGES


SHARE
Back to Top