A Class of Bidirectional Associative Neural Networks Based on Alternative Projection

Zhang Shengwei; Yang Zongkai & Zou Lihe

您当前的位置：

首页 >

文章列表页 >

A Class of Bidirectional Associative Neural Networks Based on Alternative Projection

更新时间：2025-12-08

- A Class of Bidirectional Associative Neural Networks Based on Alternative Projection
- Acta Electronica Sinica Issue 3, Pages: 23-29(1991)
- 作者机构：
  
  西安交通大学
- 作者简介：
- 基金信息：
- DOI：
  CLC：
- Published：1991
- 稿件说明：
移动端阅览
[1]张胜伟,杨宗凯,邹理和.基于投影原理的双向联想神经网络[J].电子学报,1991(03):23-29.

Zhang Shengwei, Yang Zongkai & Zou Lihe. A Class of Bidirectional Associative Neural Networks Based on Alternative Projection[J]. Acta Electronica Sinica, 1991, (3): 23-29.
[1]张胜伟,杨宗凯,邹理和.基于投影原理的双向联想神经网络[J].电子学报,1991(03):23-29. DOI：

Zhang Shengwei, Yang Zongkai & Zou Lihe. A Class of Bidirectional Associative Neural Networks Based on Alternative Projection[J]. Acta Electronica Sinica, 1991, (3): 23-29. DOI：

摘要

本文提出了一类新的双向联想神经网络。与以往基于能量函数的神经网络不同

该网络通过在两个不同的Hilbert空间的交替投影进行联想

因而其动态特性和稳态解可以在信号空间上进行分析且具有快速自适应自学习等优点。该网络可做为异联想存贮器或分类器。本文给出了该网络在存贮和恢复二值模式时的实验结果

表明了其优良的性能。

Abstract

A novel class of bidirectional associative neural networks （BANN） is proposed in this paper. In contrast to the more conventional technique of forming an energy metric for the neural network

the BANN performed by alternating projection between two different Hilbert space and so the BANN retain the better attributes

such as the ease of analysis in signal space

high accuracy of the steady-state solution and fast training. The network can be configured as either a heteroassociative memory or a classfier.Simulation results on storing and retrieving bipolar patterns in BANN’s are presented to show its good performance.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

No data

Related Author

No data

Related Institution

No data

⁰