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.
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.
应用推荐