Question: Which is not a reason that the error is a poor loss function for training classifiers? The loss surface is not smooth. The loss takes

Which is not a reason that the error is a poor loss function for training classifiers? The loss surface is not smooth. The loss takes too many different values. The loss surface contains large flat regions. The loss surface contains areas where the gradient is not defined
Step by Step Solution
There are 3 Steps involved in it
Get step-by-step solutions from verified subject matter experts
