摘要
分析了前向神经网络极值点附近的性态,指出基本BP算法用于分类问题时收敛缓慢的原因.我们利用梯度模的幂次去修改学习率,仿真结果表明,将此方法用于分类问题的训练时,收敛速度明显优于基本的BP算法.
The property of the extreme points of the multilayer neural networks is studied and the reason for the slow convergence rate of the standard BP algorithm in the vicinity of the extreme point is given. This paper uses the power of the gradient norm to modify the learning rate. Simulations indicate it has a superior convergnce rate for the classification problems, compared to the standard BP algorithm.
出处
《系统工程理论与实践》
EI
CSCD
北大核心
1998年第6期97-101,共5页
Systems Engineering-Theory & Practice