# Why Isn't Cross Entropy Used in SVM?

Modern neural networks use cross entropy as a loss function, because of shortcomings of MSE. So, why is MSE still being used in SVM (and maybe other learners) and not replaced by cross entropy?

• cross entropy is preferred for classification, while mse is preferred for regression – Thomas W Jun 8 '17 at 13:26
• stackoverflow.com/questions/36515202/… – Thomas W Jun 8 '17 at 13:27
• @ThomasW You mean it's possible to use CE in SVM? – Mehrin Jun 8 '17 at 15:14
• I'm not familiar with SVM. But I just wanted to point out that Modern neural networks use cross entropy as a loss function is not true. It just depends on the task – Thomas W Jun 8 '17 at 15:30