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.
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.
出处
《系统工程理论与实践》
EI
CSCD
北大核心
2003年第2期106-110,共5页
Systems Engineering-Theory & Practice
基金
湖北大学重点基金资助 ( A0 0 0 1 )
关键词
前馈神经网络
进化规划
逐步二次规划
结构优化
feed-forward neural networks
evolutionary programming
structure optimization
sequential quadratic programming