| 基函数神经网络权值直接确定的图像复原 |
| |
| 引用本文： | 田启川,田茂新,杨晓飞. 基函数神经网络权值直接确定的图像复原[J]. 计算机工程与应用, 2013, 49(8): 178-181 |
| |
| 作者姓名： | 田启川 田茂新 杨晓飞 |
| |
| 作者单位： | 太原科技大学 电子信息工程学院，太原 030024 |
| |
| 摘 要： | 给出了基函数神经网络图像复原的模型，该神经网络模型是由三层构成的前向神经网络，以一组正交基为隐层神经元的激励函数。为了避免反复迭代权值修正的冗长BP训练过程，提出了一种权值直接确定的算法。实验结果表明，该种权值直接确定算法不仅能一步确定权值而获得更快的运算速度，而且能达到更高的精度。
|
| 关 键 词： | 图像复原 基函数神经网络 正交基 权值修正 权值直接确定 |
Weights-direct-determination for image restoration of basis function neural network |
| |
| TIAN Qichuan,TIAN Maoxin,YANG Xiaofei. Weights-direct-determination for image restoration of basis function neural network[J]. Computer Engineering and Applications, 2013, 49(8): 178-181 |
| |
| Authors: | TIAN Qichuan TIAN Maoxin YANG Xiaofei |
| |
| Affiliation: | College of Electronic and Information Engineering, Taiyuan University of Science and Technology, Taiyuan 030024, China |
| |
| Abstract: | A general model for image restoration of basis function neural network is presented, a feed-forward neural network adopts a three-layer structure, where the hidden-layer neurons are activated by a group of orthogonal basis functions. To avoid lengthy BP-training of the iterative weights-updating, weights-direct-determination algorithm is proposed. Experimental results show that the algorithm not only can determine the weight by one step, but also gains higher accuracy. |
| |
| Keywords: | image restoration basis function neural network orthogonal basis functions weights-updating weights-direct-determination |
|
| 点击此处可从《计算机工程与应用》浏览原始摘要信息 |
|
点击此处可从《计算机工程与应用》下载免费的PDF全文 |
