Abstract

When the input includes several regimentations and the number of some variables in some regimentations is much more than the other regimentations’, the former will weak the latter’s effect to the output, which lead to augmenting the forecasting error of the model, an entropy based self-accommodation BP neural model is introduced to solve this problem, in which the several variables of each regimentations are weighted according to its importance, so each regimentations are turned into one input respectively in the BP net work model. The improved model can take the all kinds of inputs into account entirely and reasonably, and boost the forecast accuracy, which develops the applied theory of neural network.

Keywords: BP Network, Artificial Neural Network (ANN), forecasting method, riverbed-deformation