Initial Results on Fuzzy Morphological Associative Memories

WANG Min; WANG Shi-tong; WU Xiao-jun

您当前的位置：

首页 >

文章列表页 >

Initial Results on Fuzzy Morphological Associative Memories

更新时间：2025-07-16

- Initial Results on Fuzzy Morphological Associative Memories
- Acta Electronica Sinica Vol. 31, Issue 5, Pages: 690-693(2003)
- 作者机构：
  
  1. 南京般空航天大学计算机科学与工程系,江苏,南京,210016
  2. 江南大学信息工程学院,江苏,无锡,214036
  3. 中国科学院沈阳自动化研究所机器人学重点实验室,沈阳,110015
  4. 南京般空航天大学计算机科学与工程系江苏南京,210016
  5. 江南大学信息工程学院江苏无锡,214036
  6. 中国科学院沈阳自动化研究所机器人学重点实验室沈阳,110015
- 作者简介：
- 基金信息：
- DOI：
  CLC： TP18TP391
- Published：2003
- 稿件说明：
移动端阅览
WANG Min, WANG Shi-tong, WU Xiao-jun. Initial Results on Fuzzy Morphological Associative Memories[J]. Acta Electronica Sinica, 2003, 31(5): 690-693.
DOI：

WANG Min, WANG Shi-tong, WU Xiao-jun. Initial Results on Fuzzy Morphological Associative Memories[J]. Acta Electronica Sinica, 2003, 31(5): 690-693. DOI：

摘要

人工神经网络理论已经被成功地应用于各种不同的模式识别问题.重点研究了联想记忆网络

提出了一种新的基于形态学和模糊运算的联想记忆网络

即模糊形态学联想记忆网络FMAM.它与经典联想记忆和模糊联想记忆FAM有显著不同.文中分析了FMAM的记忆能力和抗腐蚀/膨胀噪声的能力.自联想FMAM具有无限存储能力

能保证完全回忆

并且回忆在一步内完成

可模糊性解释等.仿真实验验证了自联想FMAM的良好性能.

Abstract

The theory of artificial neural networks has been successfully applied to a wide variety of pattern recognition problems.Associative memories are focused and fuzzy morphological associative memories FMAM based on morphological and fuzzy operations are presented here.The properties of FMAM are greatly different from those of classical associative memories and fuzzy associative memories.FMAM's storage capacity and tolerance capability of erosive/dilative noise are analyzed.Autoassociative FMAM has the unlimited storage capacity

perfect recall guarantee

recall in one step and fuzzy explanation.The experimental results demonstrate the effective performance of autoassociative FMAM.

关键词

Keywords

references

Views

1170

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Morphological Operators Based on Matrix Partial Ordering Relation

Data Abstraction Based on Morphological Adjusted-Weight Neural Network

Research on Quantum-Inspired Mathematical Morphology

A Video-Based Online Handwritten Chinese Character Recognition Method

Morphological Top-Hat Operator for Multisensor Images Fusion

Related Author

WANG Na

WANG Jun-ping

ZHU Jun-hui

YU Nong

JING Xiao-jun

LUO An

XIE Ke-fu

ZHEN Li-xin

Related Institution

School of Telecommunication, Xidian University

Shanghai Institute of Technical PhysicsChinese Academy of SciencesShanghai 200083China

Beijing University of Posts and TelecommunicationsBeijing 100876China

Shanghai Institute of Technical Physics,Chinese Academy of Sciences

Beijing University of Posts and Telecommunications

⁰