// Course · stage 1 of 9
Math & Programming Foundations
Linear algebra, calculus, probability and Python/NumPy/PyTorch — the toolbox for every later stage.
5 unitsabout 61 hours8 algorithms
01Units in this stage
In order. Each unit has goals, algorithms, must-read papers, a project and a self-test.
01 · U10 Python, NumPy & Tooling Read and write Python, vectorise with NumPy, use the command line, Git and Jupyter. 12 h0 algorithms0 papers 02 · U11 Linear Algebra Vector spaces, matrix multiplication, eigenvalues and SVD — the language of embeddings, attention and LoRA. 15 h2 algorithms0 papers 03 · U12 Calculus & Optimization Derivatives, partial derivatives, the chain rule and gradients — “walking downhill along the gradient”. 12 h2 algorithms1 papers 04 · U13 Probability, Statistics & Information Theory Distributions, expectation, Bayes, maximum likelihood, cross-entropy and KL divergence. 12 h3 algorithms0 papers 05 · U14 PyTorch & Autograd Tensors, autograd, data loading and the training loop. 10 h2 algorithms0 papers
02Algorithms you will meet
Algorithms Atlas →Principal Component Analysis (PCA)LoRA (Low-Rank Adaptation)Stochastic Gradient Descent (SGD)BackpropagationLogistic RegressionExpectation–Maximization (EM)Variational Autoencoder (VAE)Adam
Part of these routes: Application Developers · Algorithm Researchers · Domain Scientists