Stage 1 · Foundations
Math & Machine Learning Foundations
The minimum math and the core idea of learning from data: loss, gradients and generalisation.
3 lessons1 ready
- 01 How Machines Learn: Loss Functions and Gradient Descent The core loop of all modern AI training explained with one tiny example. Beginner 18 min ✓
- 02 The Minimum Math for AI: Vectors, Probability, Derivatives Linear algebra, probability and calculus — only the parts LLMs actually use. Intermediate 30 min ✎ In progress
- 03 Overfitting, Generalisation and Data Splits Why models that ace training data can fail in the real world, and how to measure it. Intermediate 15 min ✎ In progress
Matching units in the new course
Each unit has goals, algorithms, must-read papers, a project and a self-test.
U11 Linear Algebra Vector spaces, matrix multiplication, eigenvalues and SVD — the language of embeddings, attention and LoRA. 15 h2 algorithms0 papers U12 Calculus & Optimization Derivatives, partial derivatives, the chain rule and gradients — “walking downhill along the gradient”. 12 h2 algorithms1 papers U13 Probability, Statistics & Information Theory Distributions, expectation, Bayes, maximum likelihood, cross-entropy and KL divergence. 12 h3 algorithms0 papers U20 The ML Workflow: Data, Loss & Generalization Train/validation/test splits, overfitting, bias–variance, cross-validation and metrics. 10 h3 algorithms1 paperslesson ready