| 一种复前馈神经网络的新算法 |
| |
| 引用本文： | 张代远,王绍棣.一种复前馈神经网络的新算法[J].系统工程与电子技术,2000,22(4). |
| |
| 作者姓名： | 张代远 王绍棣 |
| |
| 作者单位： | 南京邮电学院计算机科学与技术系,210003 |
| |
| 摘 要： | 提出了一种复三层前馈网络的新型学习算法。该算法采用的是分层优化方法 ,将隐层的非线性神经元线性化 ,线性化产生的误差通过罚项受到限制。分层优化使得每一层权值整体优化 ,而与另一层无关 ,这样使得整个优化过程更有效。
|
| 关 键 词： | 算法 神经元件 网络结构 误差 |
A New Complex Algorithm About Feedforward Neural Networks |
| |
| Zhang Daiyuan,Wang Shaodi.A New Complex Algorithm About Feedforward Neural Networks[J].System Engineering and Electronics,2000,22(4). |
| |
| Authors: | Zhang Daiyuan Wang Shaodi |
| |
| Abstract: | In this paper, a new complex algorithm for training of 3-layered perceptrons is proposed, which is based on a linearization of nonlinear processing neurons and the optimization of multilayer perceptrons layer by layer. The weights in each layer are updated depending on each other in one iteration epoch, but separately from other layers. |
| |
| Keywords: | Algorithm Neural component Network structure Error |
| 本文献已被 万方数据 等数据库收录！ |
|
