Probability Distribution of Kohonen Neural Network in the Post Training Phase

胡德文; 沈实; 王正志; 温熙森

您当前的位置：

首页 >

文章列表页 >

Probability Distribution of Kohonen Neural Network in the Post Training Phase

更新时间：2025-12-08

- Probability Distribution of Kohonen Neural Network in the Post Training Phase
- Acta Electronica Sinica Issue 8, (1995)
- 作者机构：
  
  国防科技大学
- 作者简介：
- 基金信息：
- DOI：
  CLC： TP18
- Published：1995
- 稿件说明：
移动端阅览
[1]胡德文,沈实,王正志,温熙森.Kohonen网络后训练阶段自组织的密度分布[J].电子学报,1995(08):52-56.

胡德文, 沈实, 王正志, et al. Probability Distribution of Kohonen Neural Network in the Post Training Phase[J]. Acta Electronica Sinica, 1995, (8).
[1]胡德文,沈实,王正志,温熙森.Kohonen网络后训练阶段自组织的密度分布[J].电子学报,1995(08):52-56. DOI：

胡德文, 沈实, 王正志, et al. Probability Distribution of Kohonen Neural Network in the Post Training Phase[J]. Acta Electronica Sinica, 1995, (8). DOI：

摘要

本文首先将Ｋｏｈｏｎｅｎ网络的训练过程划分成两个阶段，即自组织拓扑保持映射形成阶段和训练阶段，进一步分析了后训练阶段的拓扑保持特性，神经元应有的邻域关系，神经元的竞争与感受野的划分等问题，最后定量分析了任意的外部输入概率分布下，一维神经元阵列稳定权重的概率密度分布的递推关系式，最终还得到了外部输入服从均匀分布下的稳定权重的显式解。

Abstract

The training process of Kohonen neural network is firstly divided into two phases

the formation phase of self-organizing topology preserve mapping and the post-training phase.Then an investigation is made into the topology preserve property

the neighborhood relationship

the competition and the division of receptive field of the neurons in the post-training phase.Furthermore

the quantitative analysis of probability distribution is given to the one dimensional neural array in the case of arbitrary distribution input

and the iterative formulas of the stated weights of neurons are obtained. Finally

the explicit solution of the static weights is presented to the uniform distributed input.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Real-Time Gesture Recognition Algorithm Based on LoRa Signals

Continual Learning Methods and Applications in Computer Vision

Lightweight MR Image Reconstruction Network Based on Wavelet Domain Complex Convolution and Complex Transformer

End-to-End Full Complex-Valued Domain SAR Target Classification Neural Network

Related Author

HAN Chong

DU Hao

GUO Jian

SUN Li-juan

FANG Yan

Wei Yun-chao

Cong Run-min

Zuo Wang-meng

Related Institution

College of Computer, Nanjing University of Posts and Telecommunications

Jiangsu Key Laboratory of Intelligent Sensing and Computing for Internet of Things

School of Computer Science and Technology, Beijing Jiaotong University

School of Control Science and Engineering, Shandong University

School of Computer Science and Technology, Harbin Institute of Technology

⁰