摘要
前馈神经网络的结构直接影响网络的性能。构造基于拟牛顿法(Quasi-Newton Algorithm)的前馈神经网络模型,为了优化神经网络结构,尝试引入重置算法(Early Restart Algorithm),得到基于重置的拟牛顿动态前馈神经网络。对比实验表明,重置算法的引入有效地解决了结构优化问题,优化后的神经网络具有良好的收敛性与稳定性。
The structure of feed forward neural network will affect its performance directly. The feed forward neural network based on Quasi-Newton algorithm is proposed firstly. Then, in order to optimize the neural network structure, the early restart algorithm is introduced and applied to the Quasi-Newton feed forward neural network.. The comparative experiment results demonstrate that the early restart algorithm can solve the structure optimization problem of Neural Network effectively, and the revised neural network performs well in convergence and stability.
出处
《辽宁工程技术大学学报（自然科学版）》
CAS
北大核心
2004年第4期560-563,共4页
Journal of Liaoning Technical University (Natural Science)
基金
国家自然科学基金资助项目(10271025)
关键词
重置算法
神经网络
结构优化
early restart algorithm
neural network
structure optimization
