Matrices and matrix multiplication

A matrix is a grid of numbers. Multiplying a matrix by a vector takes the dot product of each row with the vector: [[1, 2], [3, 4]] times (1, 1) gives (1 + 2, 3 + 4) = (3, 7). Each layer of a neural network is essentially one big matrix multiplication, which is why AI runs on chips built to multiply matrices quickly.

Why it matters: A layer of neurons is a matrix multiplication, so this is the arithmetic of every network.

Builds on: Vectors, The dot product and similarity

Learn it, then prove it

Sign in (free) to take this step's mastery check and save your journey.