I have read many articles which replaced cross-entropy or softmax layer with SVM classifier in neural network. Their results suggested SVM-NN (SVM as classifier) outperformed softmax, cross-entropy. (One such paper - http://deeplearning.net/wp-content/uploads/2013/03/dlsvm.pdf)
I wish to train and test SVM-NN on my datasets. I have two questions
- Is there any existing library/code available in R or python
- Can some advice on how to implement this. Later I can make it public for others also
Thanks