| 一种基于模糊推理的神经网络学习算法 |
| |
| 引用本文： | 周颢,任庆生,戚飞虎. 一种基于模糊推理的神经网络学习算法[J]. 上海交通大学学报, 2004, 38(1): 96-98,102 |
| |
| 作者姓名： | 周颢 任庆生 戚飞虎 |
| |
| 作者单位： | 上海交通大学,计算机科学与工程系,上海,200030 |
| |
| 摘 要： | 提出了一种新的神经网络学习算法．相对于其他学习算法，该算法侧重于网络参数的调整，通过对样本集的模糊推理、调整和分类学习来实现自适应的神经网络学习．结果表明，该算法能大大提高神经网络的学习速度和学习效率，并能从样本集中得到反常样本和小概率事件样本，对小概率事件样本有很好的学习能力．
|
| 关 键 词： | 人工神经网络 误差反向传播算法 模糊推理 |
| 文章编号： | 1006-2467(2004)01-0096-03 |
A Neural Network Learning Algorithm Based on Fuzzy Deduction |
| |
| ZHOU Hao,REN Qing-sheng,QI Fei-hu. A Neural Network Learning Algorithm Based on Fuzzy Deduction[J]. Journal of Shanghai Jiaotong University, 2004, 38(1): 96-98,102 |
| |
| Authors: | ZHOU Hao REN Qing-sheng QI Fei-hu |
| |
| Abstract: | A new algorithm was proposed which improves the training of neural networks. Different from previous approaches, this new approach focuses on the samples. With self-adaptive fuzzy deduction, classification and classified training, it achieves a better training performance. This algorithm was tested and works quite well. Besides its efficiency, the good ability to detect abnormal and low-probable samples is also worth notice. |
| |
| Keywords: | artificial neural network error back propagation algorithm (BP) fuzzy deduction |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
