| 权值光滑BP算法：一种改善网络推广性能的方法 |
| |
| 引用本文： | 孙晓艳,李飒,马远良.权值光滑BP算法：一种改善网络推广性能的方法[J].系统仿真学报,2001,13(1):64-66. |
| |
| 作者姓名： | 孙晓艳 李飒 马远良 |
| |
| 作者单位： | 1. 西北工业大学航海工程学院,
2. Information System Research Lab,School ofEE. Nanyang Technological University Singapore 639798 |
| |
| 摘 要： | 推广性能是人工神经网络研究的重要方向。在推广性能的研究中，改进学习算法是提高前向网络推广性能的重要方法之一。本文对一特殊的权值光滑BP算法的理论基础进行了仔细的研究，并将该算法首次应用于水声目标的分类问题。实验结果表明，具有权值光滑BP算法的前向网络不仅具有较光滑的连续权值，而且其推广性能也优于具有标准BPM算法的前向网络。
|
| 关 键 词： | 推广性能 光滑权值 BP算法 人工神经网络 |
| 文章编号： | 1004-731X(2001)01-0064-03 |
| 修稿时间： | 1999年11月3日 |
Weight Smoothing BP
Algorithm: A Method to Improve Network Generalization |
| |
| SUN Xiao-yan,LI Sa,MA Yuan-liang.Weight Smoothing BP
Algorithm: A Method to Improve Network Generalization[J].Journal of System Simulation,2001,13(1):64-66. |
| |
| Authors: | SUN Xiao-yan LI Sa MA Yuan-liang |
| |
| Institution: | SUN Xiao-yan1,LI Sa2,MA Yuan-liang1 |
| |
| Abstract: | The problem of generalization ability of feedforward artificial neural networks (FFANN's) is one of the main obstacles in this field. It is of great interest for both theoretical analysis and practical application. The basic theory of a special kind of algorithms with smooth weights is discussed in this paper and for the first time, the algorithm is used for sonar target classification problems to improve the generalization ability of FFANN's .The results verified its effectiveness. |
| |
| Keywords: | feedforward artificial neural network generalization ability: smooth weight BP algorithm |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
