softmax loss 与cross-entropy loss的区别

Technically no because "softmax loss" isn't really a correct term, and "cross-entropy loss" is. So cross-entropy loss is really the correct term to use when describing the function: 

The softmax classifier is a linear classifier that uses the cross-entropy loss function. In other words, the gradient of the above function tells a softmax classifier how exactly to update its weights using something like gradient descent.

So in short, they aren't the same. However, people use the term "softmax loss" when referring to "cross-entropy loss" and because you know what they mean, there's no reason to annoyingly correct them. Because they are used interchangeably, the two terms are effectively the same

softmax loss函数是指针对softmax分类器的损失函数，是一种泛指；可以使用mse也可以是cross-entropy loss函数或其他种类；交叉熵损失函数只统计正确的部分；而mse是统计错误的部分；