摘要
反向传播神经网络的研究，最重要的任务之一是改善训练时间。本文提出了两种用来减少训练时间的新方法，这两种新方法是在传统和典型方法基础上的适当修改。我们给出了一些应用修改后的反向传播算法、计算机实验后的有兴趣的结果。
Improvement of the training time is one of the most important tasks in the development of the back-propagation neural nets.In this paper two new methods for reducing the training time are presented.The approach is based on an adequate modification of the traditional and classical method.Some interesting results of computer experimentations with the modified back-propagaton algorithm are provided.
出处
《小型微型计算机系统》
CSCD
北大核心
1996年第11期69-72,共4页
Journal of Chinese Computer Systems
关键词
神经网络
训练时间
反向传播
算法
Neural networks
Training algorithms
Training pairs
Back-propagation
