| 前馈神经网络结构新型剪枝算法研究 |
| |
| 引用本文： | 孙环龙,王汝凉,李双,查本波,张珊珊.前馈神经网络结构新型剪枝算法研究[J].广西师院学报,2013(4):55-60. |
| |
| 作者姓名： | 孙环龙 王汝凉 李双 查本波 张珊珊 |
| |
| 作者单位： | 广西师范学院计算机与信息工程学院,广西南宁530023 |
| |
| 基金项目： | 国家自然科学基金（60864001） |
| |
| 摘 要： | 研究神经网络的结构优化，提出采用基于贡献值与输出连接的权重来修剪节点，节点是直接剪枝而不是消除存有内在联系的节点；该方法认为神经元贡献值低于阈值，那么此神经元就是毫无意义的，同时将该算法应用于非线性函数逼近，实验结果表明，在不牺牲网络性能的情况下，采用新型剪枝算法来修剪神经网络节点是非常有意义的，所提出的算法也是非常有效的。
|
| 关 键 词： | 多层前馈神经网络 输入和隐含层神经元修剪 权重 非线性函数逼近 |
A New Pruning Algorithm for Feedforward Neural Network |
| |
| SUN Huan-long,WANG Ru-liang,LI shuang,ZHA Ben-bo,ZHANG Shan-shan.A New Pruning Algorithm for Feedforward Neural Network[J].Journal of Guangxi Teachers College(Natural Science Edition),2013(4):55-60. |
| |
| Authors: | SUN Huan-long WANG Ru-liang LI shuang ZHA Ben-bo ZHANG Shan-shan |
| |
| Institution: | (College of Computer ＆ Information Engineering, Guangxi Teachers Education University, Nanning 530023,China) |
| |
| Abstract: | In this paper ,based on the value and contribution of weights connected to the output node pruning ,pruning nodes are not directly linked to eliminate the inherent node ;neurons contribute to the method that is below the threshold value ,then the neuron is meaningless .Meanwhile ,the algo-rithm is applied to nonlinear function approximation ,the results show that the network performance without sacrificing the case ,using new pruning algorithm neural network node pruning is very mean-ingful that the proposed algorithm is also very effective . |
| |
| Keywords: | multilayer feedforward neural networks input and hidden layer neuron pruning weight contribution nonlinear function approximation |
| 本文献已被 维普 等数据库收录！ |
