I'm taking the Udacity/Google's Deep Learning course.
For problem set 2, we are training an SGD model.
One can tune the hyper-parameters (
batch_size, number of hidden hidden layers, number of nodes per hidden layer, etc) using techniques described here:
But how do I choose the
num_steps? Also through hyper-parameter tuning?
Or should I look at the validation score and continue training until there is little or no improvement? If so, is there a name for this technique and does Tensorflow have this built in?