| 摘要: |
| 为避免ＢＰ算法本身易陷入局部极小值的缺陷，本文将具有新组合激活函数的ＢＰ法与传统的ＢＰ方法（标准和带动量项）分别与统计最优化方法相结合组成混合算法，将他们分别应用于天气预报和贷款之中，并进行了仿真比较，在预报准确率和学习速度方面获得了比较满意的结果．本模拟程序在Ｔｕｒｂｏ－Ｐａｓｃａ／６．０环境下编制，在ＩＢＭＰＣ３８６和４８６机器上调试通过并运行． |
| 关键词: 人工神经元网络 最优组合函数 Madaline网络 天气预报 |
| DOI： |
| 分类号: |
| 基金项目:本文研究得到国防科工委国防科技预研基金和航天基金的资助. |
|
| FORWARD NEURAL NETWORK BASED ON HYBRID ALGORITHM OF BP WITH NEW ACTIVATION FUNCTION AND STATISTICS AND THE APPLICATIONS |
|
Jiang Tianji,Yuan Zengren
|
| Abstract: |
| In order to avoid the disadvantage of BP algorithm, which is to trap into thelocal minimum, this paper provides Hybrid Algorithm consisted of BP with new combination activation function and statistics; then this new algorithm is applied to weather forecast and loan and the results are compared with Hybrid Algorithm based on backpropagation(standard and momentum-term) and statistics. Simulation results show that the accuracy and learning rate of prediction are both satisfactory. This program is written inTURBO-PASCAL 6. 0 and run on IBM PC/386 and 486. |
| Key words: ANN （artificial neural networks ） OCAF （optimal combination activationfunction） MNN（madaline neural networks） weather forecasting |
