Design of Dynamic Neural Network Based on the Sensitivity Analysis of Model Output

HAN Hong-gui; LI Miao; QIAO Jun-fei; BR

您当前的位置：

首页 >

文章列表页 >

Design of Dynamic Neural Network Based on the Sensitivity Analysis of Model Output

更新时间：2025-07-16

- Design of Dynamic Neural Network Based on the Sensitivity Analysis of Model Output
- Acta Electronica Sinica Vol. 38, Issue 3, Pages: 731-736(2010)
- 作者机构：
  
  北京工业大学电子信息与控制工程学院,北京,100124
- 作者简介：
- 基金信息：
- DOI：
  CLC： TP183
- Published：2010
- 稿件说明：
移动端阅览
HAN Hong-gui, LI Miao, QIAO Jun-fei, et al. Design of Dynamic Neural Network Based on the Sensitivity Analysis of Model Output[J]. Acta Electronica Sinica, 2010, 38(3): 731-736.
DOI：

HAN Hong-gui, LI Miao, QIAO Jun-fei, et al. Design of Dynamic Neural Network Based on the Sensitivity Analysis of Model Output[J]. Acta Electronica Sinica, 2010, 38(3): 731-736. DOI：

摘要

FONT face=Verdana>

<FONT face=Verdana>神经网络的性能由其训练算法和拓扑结构共同确定。为了解决设计网络结构的动态调整问题，论文给出了一种神经网络结构动态设计方法。以隐含层神经元输出的贡献对模型输出敏感度进行分析，从而调整神经网络结构，对贡献太小的神经元予以删除，对贡献值太大的神经元利用最邻近法在其附近插入新的神经元。通过对非线性函数进行逼近和对非线性系统关键参数进行预测证明了该方法的有效性。

Abstract

The capabilities of neural networks are influenced by the learning algorithms and the topologies. Thus

in order to solve the problem of dynamic topologies

a new design method for dynamic structure of neural network is proposed in this paper. The dynamic design for neural network is based on the sensitivity analysis (SA) of the model output. This algorithm can delete the nodes in the hidden layer whose contribution ratios are too little; and add new nodes to the hidden layer whose ratios are too large relied on the the nearest neighbor interpolation. Finally

This proposed algorithm is used to track the nonlinear functions and predict the nonlinear systems

the results demonstrate the good effect of the dynamic feed-forward neural network (SAFNN).

关键词

Keywords

references

Views

1432

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Image Classification Network of Background Perception Mechanism

Neural Network Based Image Style Transfer: A Survey

Integrated Structural Electromagnetic Optimization Design of Mesh Antennas Based on Adaptive Space Mapping Multi-Fidelity Model

Differential Coding and Neural Network-Aided Channel Estimation in OFDM Systems

Related Author

YUAN Heng

RAN Chao

ZHANG Sheng-chong

WANG Wei

ZHANG Jing-yi

WEN Yu-hui

WEI Yun-chao

TAN Yu-zheng

Related Institution

School of Software, Liaoning Technical University

Key Laboratory of Optoelectronic Information Control and Security Technology

School of Computer Science and Technology, Beijing Jiaotong University

State Key Laboratory of Integrated Electromechanical Manufacturing of High-performance Electronic Equipments, Xidian University

School of Electrical Engineering & Electronic Information, Xihua University

⁰