Course details
Machine Learning
Learn what ML engineers do, then the maths underneath machine learning: vectors and matrices, derivatives and gradients, probability and statistics. Finish by sorting problems into supervised, unsupervised, semi-supervised, self-supervised and reinforcement learning, all on one small dataset of flats for rent.
Course curriculum
Introduction to the ML Engineer3 lessons
See what an ML engineer actually does day to day, how the role differs from an AI engineer, and the skills and responsibilities the rest of this course builds.
Linear Algebra4 lessons
Turn flats into vectors and tables into matrices, multiply them to predict every rent at once, and learn when a matrix can be inverted and what eigenvalues reveal.
Calculus3 lessons
Use derivatives to measure how a loss responds to each weight, chain them together for layered models, and collect them into gradients, Jacobians and Hessians.
Probability4 lessons
Count your way to probabilities, flip conditions with Bayes' theorem, describe uncertain numbers as random variables, and match everyday stories to the standard distributions.
Statistics3 lessons
Describe a dataset by its centre, spread and outliers, pick the chart that answers the question, and estimate a whole population from a sample with honest uncertainty.
Types of Machine Learning5 lessons
See what makes a program learn, then sort problems into supervised, unsupervised, semi-supervised, self-supervised and reinforcement learning by asking where the answers come from.