然后给出了一个具体的拟合算法实例，探讨了神经网络参数对于学习过程及拟合结果的影响；

Then, an example of the fitting arithmetic is given, and the infection by the neural network parameter on the fitting result is researched.

youdao

对于参数的学习，提出了一种适用于分类器的可微经验风险函数，该函数能够有效地利用梯度下降法进行最小化。

For the learning process, a new kind of empirical risk function is proposed which is differentiable and can be minimized by gradient descent strategy.

youdao