Data Abstraction Based on Morphological Adjusted-Weight Neural Network

JING Xiao-jun; YU Nong

您当前的位置：

首页 >

文章列表页 >

Data Abstraction Based on Morphological Adjusted-Weight Neural Network

更新时间：2025-07-16

- Data Abstraction Based on Morphological Adjusted-Weight Neural Network
- Acta Electronica Sinica Vol. 33, Issue 3, Pages: 397-401(2005)
- 作者机构：
  
  1. 北京邮电大学,北京,100876
  2. 中国科学院上海技术物理研究所,上海,200083
  3. 北京邮电大学北京,100876
  4. 中国科学院上海技术物理研究所上海,200083
- 作者简介：
- 基金信息：
- DOI：
  CLC： TP317.4
- Published：2005
- 稿件说明：
移动端阅览
JING Xiao-jun, YU Nong. Data Abstraction Based on Morphological Adjusted-Weight Neural Network[J]. Acta Electronica Sinica, 2005, 33(3): 397-401.
DOI：

JING Xiao-jun, YU Nong. Data Abstraction Based on Morphological Adjusted-Weight Neural Network[J]. Acta Electronica Sinica, 2005, 33(3): 397-401. DOI：

摘要

本文研究了模式样本的选取操作要领和典型样本数据的精炼方法.为改善神经网络普遍存在着误差精度与收敛速率对初始权值颇为敏感甚至过于依赖的缺陷

采用感受野的Gabor函数模型来优化网络权值的初始量.这不仅能为学习过程提供一个良好的开端

重要的是将赋予网络模型以具备可塑性优化的基础和适应环境变化的潜力.算法运用主成份数学分析法对结构元分量的贡献率进行了统计度量与计算

以提取出对滤波运算最具影响力的主要分量

从而可显著降低数据处理量

使运行速度和学习效率更高.

Abstract

The selective operation of pattern sample and abstracting method of typical sample data are discussed in this paper.In order to improve obvious shortcoming existing in neural networks in which error precision and convergent rate will be sensitive to initial weight values

even more depending on them

the Gabor function model of visual perception field is applied to optimize initial weight value of neural networks.In this way a good start in learning process can be provided.It is more important to obtain plastic superiority adaptive to complicated alterable environment for the neural network model

and to implement optimal computing principle in which operation load of structuring element weights in morphological filter can be distributed according to their contributive rate.

关键词

Keywords

references

Views

803

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

DRHA-UIE: An Underwater Image Enhancement Method Based on Dual Residual Hybrid Attention Block

Research on Quantum-Inspired Mathematical Morphology

Survey of Object Detection Based on Deep Learning

Visual Object Tracking Algorithm Based on Adaptive Feature Selection

Related Author

WANG Xin

SHI Hui

XIE Ke-fu

LUO An

LUO Hui-lan

CHEN Hong-kun

WANG Cai-xia

AN Qi

Related Institution

College of Computer Science and Technology， Jilin University

College of Information Science and Engineering,Central South University Changsha

School of Information Engineering, Jiangxi University of Science and Technology

School of Electronic Information and Engineering, Changchun University of Science and Technology

Jilin Province Technology Research Center of Photoelectric Detection and Intelligent Information Processing

⁰