I have created a CNN for use on the MNIST dataset for now (so I have 10 classes). I have trained SVMs on the sublayers of this trained CNN and wish to combine them into a combined SVM as to give a combined score.
So far, I trained two individual SVMs at two of the sublayers of my neural network. What is the best method I can go about combining the two SVMs and what are the different options available to me? Is it simply a case of taking the maximum/average of each SVM prediction for a class and using that as the score for the combined SVM class prediction?