首页 | 本学科首页   官方微博 | 高级检索  
     

基于模糊推理的自适应BP算法
引用本文:汪德馨 王宇川. 基于模糊推理的自适应BP算法[J]. 系统工程学报, 1997, 12(1): 55-62
作者姓名:汪德馨 王宇川
作者单位:天津大学系统工程研究所
摘    要:BP网络是迄今为止应用最广泛的一种神经网络,但这种算法也存在着收敛速度慢、容易陷入局部极小点等问题.本文在标准BP算法的基础上提出一种改进BP算法,称之为自适应BP算法.这种自适应BP算法采用模糊规则动态调整学习参数,并且能在学习过程中和学习完成后通过隐节点调整算法优化网络结构,有比标准BP算法更好的收敛性和更好的泛化能力

关 键 词:神经网络,BP算法,模糊推理

ADAPTIVE BP ALGORITHM BASED ON FUZZY REASONING
Abstract:BP algorithm is probably the most popular and widely used neural networks. However, the algorithm has a low convergence rate and is easily trapped in local minima. In this paper, we present a new algorithm based on the standard BP algorithm, called adaptive BP algorithm. The adaptive BP algorithm uses a fuzzy controller to adjust the learning parameters dynamically and is able to optimize the network structure by adjusting the number of hidden nodes during and after training procedure. The adaptive BP algorithm has been tested to have higher convergence rate and perform better in generalization.
Keywords:neural network   BP algorithm   fuzzy reasoning  
本文献已被 CNKI 维普 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号