扩展交替投影神经网络 ——具备联想记忆功能的充分必要条件

王金根; 龚沈光; 陈世福

您当前的位置：

首页 >

文章列表页 >

扩展交替投影神经网络 ——具备联想记忆功能的充分必要条件

论文 | 更新时间：2025-07-16

- 扩展交替投影神经网络 ——具备联想记忆功能的充分必要条件
- Sufficient and Necessary Condition of the Extended Alternating Projection Neural Network Configured as a Content Addressable Memory
- 电子学报 2004年32卷第4期页码：596-600
- 作者机构：
  
  1. 南京大学计算机软件新技术国家重点实验室,江苏,南京,210093
  2. 海军工程大学,湖北,武汉,430033
- 作者简介：
- 基金信息：
- DOI：
  中图分类号： Q811.1TN911.72O235
- 纸质出版：2004
- 稿件说明：
移动端阅览
王金根, 龚沈光, 陈世福. 扩展交替投影神经网络 ——具备联想记忆功能的充分必要条件[J]. 电子学报, 2004,32(4):596-600.

WANG Jin-gen, GONG Shen-guang, CHEN Shi-fu. Sufficient and Necessary Condition of the Extended Alternating Projection Neural Network Configured as a Content Addressable Memory[J]. Acta Electronica Sinica, 2004, 32(4): 596-600.
王金根, 龚沈光, 陈世福. 扩展交替投影神经网络 ——具备联想记忆功能的充分必要条件[J]. 电子学报, 2004,32(4):596-600. DOI：

WANG Jin-gen, GONG Shen-guang, CHEN Shi-fu. Sufficient and Necessary Condition of the Extended Alternating Projection Neural Network Configured as a Content Addressable Memory[J]. Acta Electronica Sinica, 2004, 32(4): 596-600. DOI：

摘要

对交替投影神经网络(APNN)的连接权矩阵进行修改

将其应用范围从实数域拓展到复数域

从而得到一种新的神经网络——扩展交替投影神经网络(Extended Alternating Projection Neural Networks).对EAPNN网络进行深入研究后

给出了网络稳态值的通用数学表达式

并从表达式中推出了网络具备联想记忆功能的充分必要条件.最后设计仿真实验对文中的理论分析结果进行了验证.

Abstract

The paper extends the original Alternating Projection Neural Network(APNN) and proposes an Extended Alternating Projection Neural Network (EAPNN) which functions in the field of complex numbers.An improved weight-learning approach

which permits linear dependence of complex patterns

has been presented.A general mathematical expression of the EAPNN steady-state solution has been obtained.From the general mathematical expression we have derived the sufficient and necessary condition of the EAPNN configured as a content addressable memory.In addition

simulation experiments have been designed to verify the theoretical analyses in the paper.Finally it is pointed out that the EAPNN has been applied to signal processing such as band-limited signal extrapolation

notch filter and weak-signal separation.

关键词

Keywords

references

浏览量

1084

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于交替投影神经网络的带限信号外推算法

基于LoRa信号的实时手势识别算法

连续学习方法与其在视觉任务中的应用

端到端全复数域SAR目标分类神经网络