rate of normal approximation 正态逼近速度
·2,447,543篇论文数据，部分数据来源于NoteExpress
With the best polynomial approximation as a metric, the rate of approximation of the neural networks with single hidden layer to a continuous function is estimated by using a constructive approach.
以最佳多项式逼近为度量，用构造性方法估计单隐层神经网络逼近连续函数的速度。
What are the ways in terms of matching these rate constants that we can get to the approximation. To a diagram that looks like that?
如何使这些速率常数,和我们的近似相匹配呢,达到像图表中所画的那样？
So the different ways of creating that approximation are if, and the length of the arrows now is going to be proportional to the rate.
所以产生那个近似的不同方法是如果，箭头的长度现在，和速率成正比。
应用推荐