Question

Which of the following are true when comparing ANNs and SVMs?
A) ANN error surface has multiple local minima while SVM error surface has only one minima
B) After training, an ANN might land on a different minimum each time, when initialized with random weights during each run.
C) In training, ANN's error surface is navigated using a gradient descent technique while SVM's error surface is navigated using convex optimization solvers.
D) As shown for Perceptron, there are some classes of functions that cannot be learnt by an ANN. An SVM can learn a hyperplane for any kind of distribution.

Answer 1

ANN error surface has multiple local minima While SVMerror surface has only one minima

Answer 2

ANN error surface has multiple local minima while SVM error surface has only one minima is a true statement. Therefore, among the following options, option A is the correct one for the comparison between ANN and SVMs. SVMs have simple geometric interpretation which can give a sparse solution and it does not depends on the dimensionality of the input space.