This is something to keep in mind when you start using Python. To get a true matrix multiplication, you need to use the dot() function. If you have two matrices, A and B, you can multiply them with ...

so they aren’t constrained by Python’s limitations. NumPy provides a specialized array type that is optimized to work with machine-native numerical types such as integers or floats.

It's possible to install Python and NumPy separately, however ... If you're familiar with matrix multiplication, notice that the two for-loops that compute the hidden node sum of products are just ...

However, before we clap ourselves on the back and move on, can we go even faster? Let's change our script a bit and replace the Python list with a NumPy array: import numpy as np list = ...

Gommers added, "Really long-term I expect the NumPy 'execution engine' (i.e., the C and Python code that does the heavy lifting for fast array operations) to become less and less relevant ...