AI & ML Engineering · Unit 5 · Machine Learning

Mathematics for Machine Learning

The linear algebra, calculus and optimisation that models are built on.

  1. 5.1

    Vectors and Matrices

    Vectors, matrices, dot products and matrix multiplication.

    Video
  2. 5.2

    Linear Transformations

    What a matrix does to data, plus eigenvalues and eigenvectors.

    Video
  3. 5.3

    Derivatives and Gradients

    Derivatives, partial derivatives, the chain rule and the gradient.

    Video
  4. 5.4

    Gradient Descent

    Minimising a loss function step by step, and the role of the learning rate.

    Video
  5. 5.5

    Probability for ML

    Likelihood, maximum likelihood estimation and cross-entropy.

    Video
  6. 5.6

    Distance and Similarity

    Norms, Euclidean distance and cosine similarity: how models measure how alike two things are.

    Video

Unit project

Linear regression trained with gradient descent, written from scratch in NumPy and checked against scikit-learn.

Paid learners get the full brief, submit it from their dashboard and have it reviewed. It goes in your portfolio.

Open every unit

Enrol once to open every unit, its videos and a reviewed project for your portfolio.