Week 2- Understanding Python Broadcasting

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

I’m a bit confused with Python broadcasting. It is not conducting matrices calculations. Is it only for array element wise calculations? Thanks!

2

Hi Ketyeth,

For multiplying two matrices, use the dot () method. Here is an introduction to numpy.dot( a, b, out=None)

Few specifications of numpy.dot:

  • If both a and b are 1-D (one dimensional) arrays – Inner product of two vectors (without complex conjugation)
  • If both a and b are 2-D (two dimensional) arrays – Matrix multiplication
  • If either a or b is 0-D (also known as a scalar) – Multiply by using numpy.multiply(a, b) or a * b.
  • If a is an N-D array and b is a 1-D array – Sum product over the last axis of a and b.
  • If a is an N-D array and b is an M-D array provided that M>=2 – Sum product over the last axis of a and the second-to-last axis of b:

Also, dot(a, b)[i,j,k,m] = sum(a[i,j,:] * b[k,:,m])

image
image882×476 9.42 KB

If you still have questions let me know.

3

No, broadcasting can also allow you to perform an operation between a matrix and a vector, if the vector can be expanded to match the dimension of the matrix. I think I already gave you this example on another thread.