利用进化规划和逐步二次规划实现前馈神经网络的结构优化

金聪

系统工程理论与实践 ›› 2003, Vol. 23 ›› Issue (2) : 106-110.

PDF(176 KB)
PDF(176 KB)
系统工程理论与实践 ›› 2003, Vol. 23 ›› Issue (2) : 106-110. DOI: 10.12011/1000-6788(2003)2-106
论文

利用进化规划和逐步二次规划实现前馈神经网络的结构优化

    金聪
作者信息 +

Structure Optimization for Feed-forward Neural Networks Based on Evolutionary Programming and Sequential Quadratic Programming

    Cong JIN
Author information +
文章历史 +

摘要

用进化规划与逐步二次规划来实现前馈神经网络的结构优化问题 ,并提出了一个相应的学习算法 .针对进化规划与逐步二次规划各自的特点 ,进行了组合 ,使算法不仅具有随机全局搜索能力 ,而且还具有更好的全局收敛能力 ,并与环境有更强的自适应能力 .最后通过仿真和应用实验证实了算法的有效性.

Abstract

In this paper, when evolutionary programming and sequential quadratic programming are applied to the structure optimization of feed-forward neural networks, a learning algorithm is proposed. The new algorithm retains the ability of stochastic global searching. It has better global convergence and very strong self-adaptive ability with environment. The efficiency of research work mentioned above has been shown by simulation and applications.

关键词

前馈神经网络 / 进化规划 / 结构优化 / 逐步二次规划

Key words

feed-forward neural networks / evolutionary programming / structure optimization / sequential quadratic programming

引用本文

导出引用
金聪. 利用进化规划和逐步二次规划实现前馈神经网络的结构优化. 系统工程理论与实践, 2003, 23(2): 106-110 https://doi.org/10.12011/1000-6788(2003)2-106
Cong JIN. Structure Optimization for Feed-forward Neural Networks Based on Evolutionary Programming and Sequential Quadratic Programming. Systems Engineering - Theory & Practice, 2003, 23(2): 106-110 https://doi.org/10.12011/1000-6788(2003)2-106
PDF(176 KB)

Accesses

Citation

Detail

段落导航
相关文章

/