DL SP: Course: 1: Week2, practice_python_with_numpy, Exercise 7 - softmax

I cannot understand what it implies, Can anyone help me to solve the wrong intuition about it?

1. Softmax should be performed for all features of each training example, so softmax would be performed on the columns (once we switch to that representation later in this course).

2. what is the difference between Softmax and normalize_rows

Thank you

Softmax is basically an activation function which we use to normalize the output of the neural network. After normalizing , each output gets in the range of 0 to 1. Basically, scaling numbers into probabilities.