Research on Monolithic Fuzzy Neural Networks Self-Learning problem

王振峰; 靳东明; 李志坚

您当前的位置：

首页 >

文章列表页 >

Research on Monolithic Fuzzy Neural Networks Self-Learning problem

更新时间：2025-12-08

- Research on Monolithic Fuzzy Neural Networks Self-Learning problem
- Acta Electronica Sinica Issue 2, (1997)
- 作者机构：
  
  清华大学微电子所
- 作者简介：
- 基金信息：
- DOI：
  CLC： TP183
- Published：1997
- 稿件说明：
移动端阅览
[1]王振峰,靳东明,李志坚.单体模糊神经网络自学习问题研究[J].电子学报,1997(02):33-38.

王振峰, 靳东明, 李志坚. Research on Monolithic Fuzzy Neural Networks Self-Learning problem[J]. Acta Electronica Sinica, 1997, (2).
[1]王振峰,靳东明,李志坚.单体模糊神经网络自学习问题研究[J].电子学报,1997(02):33-38. DOI：

王振峰, 靳东明, 李志坚. Research on Monolithic Fuzzy Neural Networks Self-Learning problem[J]. Acta Electronica Sinica, 1997, (2). DOI：

摘要

本文采用的单体模糊神经网络（ＭＦＮＮｓ）在智能控制中兼有模糊控制与人工神经网络控制的特点，不仅具有良好的控制特性，而且能够进行模型自学习和在线自调整．结合本身结构、人工神经网络理论和模糊理论，可得到ＭＦＮＮｓ自学习的一系列算法．本文对基于ＡＮＮｓ梯度算法的ＭＦＮＮｓ进行了研究，结果表明，ＭＦＮＮｓ结构的自学习、自调整是可行、简便和有效的，有比一般ＡＮＮｓ快得多的收敛性，能够成功地应用于智能控制系统，包括复杂对象的控制．此外所提出的学习方法很容易以ＶＬＳＩ硬件实现．

Abstract

MFNNs（Monolithic Fuzzy Neural Networks）proposed in this paper combine the advantages of Fuzzy Logic Control and Aritificial Neural Network Control

not only behave well in object control but also have abilities of model self-learning and on-line self-adjustment. A series of self-learning algorithms for MENNs can be obtained based on ANNs theory

Fuzzy Set theory and its special structure. Some simulation results based on MFNNs gradient algorithm show that the convergence performance of MFNNs is much better than ordinary ANNs

the self-learning and self-adjustment are practicable

simple and effective. The learning model can be used for intelligent control system including the complicated object control. The VLSI realization of the learning MFNNs can be implemented easily.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Monolithic Fuzzy Neural Network（MFNNs）：Application in Intelligent Control＆VLSI Realization

A Collaborative Multi-Agent Model for Database Parameter Tuning

On the Finite Strong Completeness of NM321;

The Temperature Compensation for Pressure Sensor Based on Artificial Neural Network

Related Author

王振峰

靳东明

李志坚

LI Jiang-min

QIAO Shao-jie

HAN Nan

WU Tao

GAO Rui-wei

Related Institution

清华大学

School of Cyber Security and Information Law， Chongqing University of Posts and Telecommunications

School of Management， Chengdu University of Information Technology

School of Software Engineering， Chengdu University of Information Technology

2.University of Science and Technology Beijing

⁰