| 一个基于机器学习的神经网络初始化方法 |
| |
| 引用本文： | 王继成.一个基于机器学习的神经网络初始化方法[J].计算机研究与发展,1997,34(8):599-604. |
| |
| 作者姓名： | 王继成 |
| |
| 作者单位： | 同济大学计算机系 |
| |
| 摘 要： | 本文针对ＢＰ前馈神经网络存在的训练时间长、容易陷入局部极小等问题，研究了一个基于机器学习的神经网络初始化方法。实验结果表明，用这种方法初始化神经网络，提高了神经网络的学习效率和泛化能力，并且可以有效地抑制陷入局部极小的可能性。
|
| 关 键 词： | 前馈神经网络 网络初始化 机器学习 神经网络 |
A METHOD OF NEURAL NETWORK INITIALIZATION BASED ON MACHINE LEARNING |
| |
| WANG Ji Cheng\ WANG Xun.A METHOD OF NEURAL NETWORK INITIALIZATION BASED ON MACHINE LEARNING[J].Journal of Computer Research and Development,1997,34(8):599-604. |
| |
| Authors: | WANG Ji Cheng\ WANG Xun |
| |
| Abstract: | In order to solve the problem of long training time and local minima in BP neural network, a method of neural network initialization based on machine learning is studied in this paper. The experiment results show that the learning efficiency and generalization ability of the initialized neural network are increased and the probability of falling to local minima is decreased. |
| |
| Keywords: | feedforward neural network back propagation algorithm network initialization machine learning |
| 本文献已被 CNKI 维普 等数据库收录！ |
