Training an associative memory model for character recognition

被引：0

作者：

Awwal, AAS ^{[1
]}

Tang, HY ^{[1
]}

机构：

[1] Wright State Univ, Dept Comp Sci & Engn, Dayton, OH 45435 USA

来源：

PHOTONIC DEVICES AND ALGORITHMS FOR COMPUTING III | 2001年 / 4470卷

关键词：

character recognition; associative memory; inner product memory; Hopfield memory; content-addressable memory; adaptive thresholding;

D O I：

10.1117/12.449670

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

In this paper, a new algorithm to determine the adaptive threshold formula for the trinary associative memory model is presented. The optimal threshold is chosen to yield the best performance. Different threshold parameters have been investigated to obtain the optimal range of threshold parameters. In order to validate our performance model, character recognition problems are investigated.

引用

页码：74 / 80

页数：7

共 7 条

[1] AN ADAPTIVE OPTOELECTRONIC NEURAL NETWORK FOR ASSOCIATIVE PATTERN RETRIEVAL
AHMED, F
AWWAL, AAS
[J]. JOURNAL OF PARALLEL AND DISTRIBUTED COMPUTING, 1993, 17 (03) : 245 - 250
[2] AHMED F, 1991, OSA ANN M OPT SOC AM, V17, P164
[3] Awwal A. A. S., 1989, Proceedings of the SPIE - The International Society for Optical Engineering, V1053, P17
[4] MACHINE PARTS RECOGNITION USING A TRINARY ASSOCIATIVE MEMORY
AWWAL, AAS
KARIM, MA
LIU, HK
[J]. OPTICAL ENGINEERING, 1989, 28 (05) : 537 - 543
[5] HOPEFIELD JJ, 1982, P NATL ACAD SCI USA, V79, P2554
[6] Karim M. A., 1989, Proceedings of the IEEE 1989 National Aerospace and Electronics Conference NAECON 1989 (Cat. No.89CH2759-9), P698, DOI 10.1109/NAECON.1989.40287
[7] KARIM MA, 1992, OPTICAL COMPUTING

← 1 →