论文部分内容阅读
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
BP network is by far the most widely used neural network, but this algorithm also has the problem of slow convergence, easy to fall into a local minimum. In this paper, an improved BP algorithm is proposed based on the standard BP algorithm, which is called adaptive BP algorithm. This adaptive BP algorithm uses fuzzy rules to dynamically adjust the learning parameters and can optimize the network structure through the hidden node adjustment algorithm during the learning process and after learning, and has better convergence and better generalization ability than the standard BP algorithm