But all their precisions are limit to one-order truncation error, and make severe accumulateerror on discrete models.
这些方法的精度都局限在一阶截断误差,在离散的网格上有严重的累积误差。
2
Many single BP networks make up of predictive model paratactically, each predictive model can not be affected each other, so the error is not accumulate.
由多个单独BP 网以并行方式构成预测模型,各子预测模型间无直接影响,因此没有误差积累。
3
As for the corrected models, the maximal relative error, the average relative error, the accumulate flow error are 5.93%, 0.93%, 0.13% respectively.