产生这种情况的两个主要原因是:(1)传统的误差反向传播方法(Back Propagation,BP)主要基于梯度下降的思想,需要多次迭代;(2)网络的所有参数都需要在训练过程中迭代确定.
基于4个网页-相关网页
模型分别采用多元逐步回归方法和反向传播方法。
The model used multiple stepwise regression method and back propagation method independently.
方法：联合应用反向传播人工神经网络和吸光度减法技术。
Method: The artificial neural network of reverse transmission and absorbance subtraction technique were used.
这一训练方法被称之为hmm的反向传播训练方法。
This approach to the training of HMM is called back propagation training approach.
应用推荐