Can anyone please explain this concept to me?

Course Q&A Deep Learning Specialization Neural Networks and Deep Learning
1

a.shape = (3,4)# b.shape = (4,1). for i in range(3): for j in range(4): c[i][j] = a[i][j] + b[j]

How do you vectorize this?

Regards!

2

If you first transpose b to be a 1 x 4 row vector, then you’re just adding it to each row of a, right?

Note that numpy supports the concept of “broadcasting”, which means that it can expand a vector by duplicating it so that you can do “elementwise” operations with a matrix, if the dimensions of the two objects are compatible in that way. Try this and watch what happens:

np.random.seed(42)
A = np.random.rand(3,4)
print("A = " + str(A))
b = np.ones((3,1))
print("b = " + str(b))
C = A + b
print("C = " + str(C))

Running that gives this:

A = [[0.37454012 0.95071431 0.73199394 0.59865848]
 [0.15601864 0.15599452 0.05808361 0.86617615]
 [0.60111501 0.70807258 0.02058449 0.96990985]]
b = [[1.]
 [1.]
 [1.]]
C = [[1.37454012 1.95071431 1.73199394 1.59865848]
 [1.15601864 1.15599452 1.05808361 1.86617615]
 [1.60111501 1.70807258 1.02058449 1.96990985]]
1 Like