Lets use the example of the SVM loss function for a single datapoint:
We can differentiate the function with respect to the weights. For example, taking the gradient with respect to Wyi we obtain:
Notice that this is the gradient only with respect to the row of W that corresponds to the correct class. For the other rows where j != yi the gradient is:
本文通过一个具体的例子介绍了支持向量机(SVM)损失函数针对权重的梯度计算方法。文中详细展示了对于正确类别和非正确类别的权重分别进行求导的过程。
975

被折叠的 条评论
为什么被折叠?



