Closed jpsember closed 7 years ago
This is what our function should look like.
We should have a custom SVM loss node that is able to dynamically determine loss (and gradient) based upon the training sample's label, yi.
Let's attempt this first with the 'toy example':
Results agree with toy example from lecture notes:
This is the function, including the SVM cost and regularization loss:
http://cs231n.github.io/linear-classify/#svm