Intelligent Neuron Models for Artificial Neural Networks

胡瑞敏; 徐正全; 姚天任; 李德仁

您当前的位置：

首页 >

文章列表页 >

Intelligent Neuron Models for Artificial Neural Networks

更新时间：2025-12-08

- Intelligent Neuron Models for Artificial Neural Networks
- Acta Electronica Sinica Issue 4, (1996)
- 作者机构：
  
  1. 武汉测绘科技大学航测与遥感信息工程学院
  2. 华中理工大学电子与信息工程系
  3. 武汉测绘科技大学航测与遥感信息工程学院华中理工大学电子与信息工程系
- 作者简介：
- 基金信息：
- DOI：
  CLC： TP18
- Published：1996
- 稿件说明：
移动端阅览
[1]胡瑞敏,徐正全,姚天任,李德仁.人工神经元网络的智能神经元模型[J].电子学报,1996(04):86-90.

胡瑞敏, 徐正全, 姚天任, et al. Intelligent Neuron Models for Artificial Neural Networks[J]. Acta Electronica Sinica, 1996, (4).
[1]胡瑞敏,徐正全,姚天任,李德仁.人工神经元网络的智能神经元模型[J].电子学报,1996(04):86-90. DOI：

胡瑞敏, 徐正全, 姚天任, et al. Intelligent Neuron Models for Artificial Neural Networks[J]. Acta Electronica Sinica, 1996, (4). DOI：

摘要

本文在仔细分析神经网络知识存储方式的基础上，指出了现有存储方式的严重不足：由大量具有简单处理能力的神经元组成的神经网络，虽然具有一定的智能处理能力，但由于每个神经元不具备复杂的处理能力，故必然导致由此构成的网络存在着诸如局部极小、收敛速度缓慢、推广能力差等缺点，尤其是难于用于实时处理系统，大大限制了神经网络的应用范围。为此，本文提出了一种新的智能型神经元模型并将它与常用的神经元模型进行了比较，后续论文“高阶神经网络及广义知识存储原理”将指出具此实现的算法可以将标准ＢＰ算法的收敛速度提高１０００倍以上

Abstract

Based on in-depth analysis of knowledge storing mode of neural networks

the inadequacy of current storing mode is pinpointed.That is to say

despite its definite intelligent processing capability.the neural neiwork made up of large numbers of neurons with simple processing capability but without complicated processing capability is bound to have such drawbacks as local minimum

slow converging rate and insufficient capability of being popularized.In particular

it can hardly be applied to real-time processing systenis

which greatly limits its range of application.To remedy such a situation

a new intelligent neuron model is proposed and compared with neuron models in common use.It is pointed out in a subsequent paper entitled "Generalized Information Storing Principle and Higher-Order Generalized Neural Networks" that the algorithm based on the intelligent neuron model can raise the converging rate of the conventional BP algorithm more than 1

000 times.

关键词

Keywords

references

Views

255

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Generalized Information Storing Principle and Higher-Order Generalized Neural Networks

On the Perceptron Convergence Theorem of the Monolithic Fuzzy Neural Networks

Analysis and Theory of High-Dimension Space Geometry for Artificial Neural Networks

A Neural Network Learning Algorithm for PCA and MCA

Real-Time Gesture Recognition Algorithm Based on LoRa Signals

Related Author

LIANG Jiu-zhen

HE Xin-gui

HUANG De-shuang

WANG Shou-jue

WANG Bai-nan

王哲

李衍达

罗发龙

Related Institution

Computer Science Institute,Zhejiang Normal University

Beijing Institute of System Engineering

Computer Science InstituteZhejiang Normal UniversityJinhuaZhejiang 321004China

Beijing Institute of System EngineeringBeijing 100101China

Lab of Artificial Neural Networks,Institute of Semiconductors,CAS

⁰