采用自适应变步长的后向传播算法（ABPM）构建了一个人工神经网络用水量预测模型。

The following paper constructs a artificial neural network - named water quantity predicting model, using automatically adapting and step-self-changing back propagation method(ABPM).

youdao

实验结果表明前馈后向传播网络的性能最好，与基准模型比较平均错误率下降54.4%。

Experiment results show that feed-forward backpropagation network achieves the best performance, which reduces average error rate by54.4%.

youdao

实验结果表明前馈后向传播网络的性能最好，与基准模型比较平均错误率下降54.4%。

Experiment results show that feed-forward backpropagation network achieves the best performance, which reduces average error rate by54.4%.

youdao