BP neural network can implement approximating nonlinear functions by arbitrary accuracy through regulating variable weight connection. This character can fit the nonlinear functions relations.
BP神经网络通过调节连接权重可以实现以任意精度逼近非线性函数,利用这一特点可对非线性函数关系进行拟合。
The relation between the study ability and the popularization ability of network at appearance of "over - fit" phenomenon during the construction of BP network model meets the uncertainty principle.
BP网络建模过程中,出现“过拟合”现象时网络学习能力与推广能力之间满足一般测不准关系。
The BP neural network is used to fit data, through which quantitative analysis of defect signal can be obtained.
采用了BP神经网络对数据进行拟合,能够实现对裂纹信号的定量识别。
应用推荐