| 学习算法对反馈神经网络故障性能的影响 |
| |
| 引用本文： | 张涛,胡东成. 学习算法对反馈神经网络故障性能的影响[J]. 清华大学学报(自然科学版), 2000, 40(7): 43-46 |
| |
| 作者姓名： | 张涛 胡东成 |
| |
| 作者单位： | 清华大学,自动化系,北京,100084 |
| |
| 基金项目： | 国家自然科学基金项目 !( 69571 0 1 7)，高等学校博士学科点基金项目! ( 940 0 334) |
| |
| 摘 要： | 以离散 Hopfield神经网络为例 ,详细研究了学习算法对反馈神经网络故障性能的影响。简要介绍了离散Hopfield神经网络及其采用的 Hebb学习算法。详细分析了连接故障在学习过程中对网络连接权值故障性能的影响。给出了网络输出状态概率分布变化的计算公式。进行了计算机仿真 ,验证了理论分析结论的正确性
|
| 关 键 词： | 反馈神经网络 学习算法 故障性能 |
| 修稿时间： | 1999-05-0 |
Effects of the learning algorithm on the faulty behavior of feedback neural networks |
| |
| ZHANG Tao,HU Dongcheng. Effects of the learning algorithm on the faulty behavior of feedback neural networks[J]. Journal of Tsinghua University(Science and Technology), 2000, 40(7): 43-46 |
| |
| Authors: | ZHANG Tao HU Dongcheng |
| |
| Abstract: | This paper studies the faulty behavior of feedback neural networks with stuck at faults during the course of learning using the discrete hopfield neural network (DHNN) as an example. DHNN and its Hebb learning algorithm are briefly introduced. Then the study analyzes the influence of link faults on the weights during learning and gives formulas for output probability distribution verification. A computer simulation verifies the accuracy the theoretical analysis. |
| |
| Keywords: | feedback neural network learning algorithm faulty behavior |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
