A Heuristic Approach for Improving Performance of Neural Network with the Optimal Brain Surgeon

YANG Zhong-jin

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

A Heuristic Approach for Improving Performance of Neural Network with the Optimal Brain Surgeon

更新时间：2026-05-27

- A Heuristic Approach for Improving Performance of Neural Network with the Optimal Brain Surgeon
- Vol. 23, Issue 3, Pages: 95-101(2006)
- 作者机构：
- 作者简介：
- 基金信息：
- DOI：
  CLC：
- Published：2006
- 稿件说明：
移动端阅览
杨钟瑾. 自顶向下优化神经网络的方法[J]. 广东工业大学学报, 2006, 23(3): 95-101.

YANG Zhong-jin. A Heuristic Approach for Improving Performance of Neural Network with the Optimal Brain Surgeon[J]. 2006, 23(3): 95-101.
杨钟瑾. 自顶向下优化神经网络的方法[J]. 广东工业大学学报, 2006, 23(3): 95-101. DOI：

YANG Zhong-jin. A Heuristic Approach for Improving Performance of Neural Network with the Optimal Brain Surgeon[J]. 2006, 23(3): 95-101. DOI：

摘要

介绍了一种自动优化神经网络的新启迪方法.这种启迪方法综合采用了快速自顶向下优化神经网络结构算法、动态优化学习参数算法和快速交叉校验算法.首先

快速自顶向下优化神经网络结构算法自动地优化神经网络结构;其次

动态优化学习参数算法动态地调整学习参数和选取优化的学习参数;随后

快速交叉校验算法的引入能有效地防止过度适应问题.实验结果显示

这种启迪方法与其它算法相比

具有更强的归纳性能、优化的网络结构和更快的学习速度.

Abstract

A new heuristic approach is proposed for the automated optimization of neural network.It combines fast optimal brain surgeon

dynamic optimization of learning parameters and fast cross-validation.The fast optimal brain surgeon optimizes architecture of neural network automatically.The dynamic optimization of learning parameters is able to dynamically vary its learning parameters and select optimal learning parameters.The fast cross-validation provides improvements of avoiding overfitting problem effectively.Experimental results demonstrate that with the heuristic approach

considerable performance gains are obtained compared to the other algorithms.This includes better generalization

optimal network architecture

and faster learning.

关键词

Keywords

references

杨钟瑾,史忠科. 快速选定神经网络优化结构的方法[J]. 计算机科学. 2005(04)

杨钟瑾,史忠科. 快速自顶向下优化神经网络结构的方法[J]. 系统仿真学报. 2005(01)

(美)MartinT.Hagan等著.神经网络设计[M]. 机械工业出版社, 2002

史忠科著.神经网络控制理论[M]. 西北工业大学出版社, 1997

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Research on Mixed-grained Pruning Method for Memristive Neural Network Accelerator

A Fast Combination Algorithm for HEVC Intra-Prediction Based on Neural Network

Single-channel Speech Separation Based on Separated SI-SNR Regression Estimation and Adaptive Frequency Modulation Network

A Research on Vehicle Carbon Emission Calculating Method Based on BP Neural Network

Sparse-view SPECT Image Reconstruction Based on Multilevel-residual U-Net

Related Author

Chen Hui

Zhou Bo

Song Li-feng

Fan Jun-yu

Lyu Jun

Zhang Rui

Li Jun-ping

Peng Mei-chun

Related Institution

School of Computer Science and Technology, Guangdong University of Technology

School of Information Engineering, Guangdong University of Technology

Huizhou Guangdong University of Technology IoT Cooperative Innovation Institute Co., Ltd.

School of Automation, Guangdong University of Technology

School of Electromechanical Engineering, Guangdong University of Technology

AI问答

⁰