- Joint, Marginal and Conditional Probabilityages 18 to 19 · on the way
- Bayes' Rule and Updating a Beliefages 18 to 19 · on the way
- Likelihood and the Maximum Likelihood Estimateages 18 to 20 · on the way
- Data as a Matrix: Rows, Features and the Targetages 18 to 20 · on the way
- Linear Regression by Least Squaresages 19 to 20 · on the way
- Gradient Descent: Following the Slope Downhillages 19 to 20 · on the way
- Logistic Regression and the Decision Boundaryages 19 to 21 · on the way
- Overfitting and the Bias-Variance Trade-offages 19 to 21 · on the way
- Regularisation: Charging for Complexityages 20 to 21 · on the way
- Cross-Validation and Honest Model Selectionages 20 to 21 · on the way
- Beyond Accuracy: Precision, Recall and the Cost of an Errorages 20 to 22 · on the way
- Decision Trees and Ensemblesages 20 to 22 · on the way
- Clustering: Structure Without Labelsages 20 to 22 · on the way
- Principal Components and Dimensionality Reductionages 20 to 22 · on the way
- From Perceptron to Multilayer Networkages 21 to 22 · on the way
- Backpropagation: Assigning Blame for an Errorages 21 to 22 · on the way
- Deep Learning: Convolution, Sequence and Scaleages 21 to 22 · on the way
- Attention as a Learned Lookupages 22 to 23 · on the way
- The Transformer Block: Heads, Residuals and Normalisationages 22 to 23 · on the way
- Tokenisation and What a Model Actually Readsages 22 to 23 · on the way
- Pretraining by Predicting the Next Tokenages 22 to 23 · on the way
- Scaling Laws and the Compute Budgetages 22 to 23 · on the way
- Adapting a Pretrained Model: Fine-Tuning and Low-Rank Updatesages 22 to 24 · on the way
- Generative Models: Learning a Distribution You Can Sampleages 22 to 24 · on the way
- Diffusion Models: Learning to Undo Noiseages 22 to 24 · on the way
- Markov Decision Processes: States, Actions and Returnages 22 to 24 · on the way
- Temporal-Difference Learning and Q-Learningages 23 to 24 · on the way
- Policy Gradients and the Actor-Critic Splitages 23 to 24 · on the way
- Learning from Human Preferences: Reward Models and Policy Optimisationages 23 to 24 · on the way
- Training Across Many Devices: Data, Model and Pipeline Parallelismages 23 to 24 · on the way
- Serving a Model: Batching, the Key-Value Cache and Quantisationages 23 to 24 · on the way
- Benchmarks and the Traps in Themages 22 to 24 · on the way
- Fairness, Accountability and the Limits of a Modelages 21 to 22 · on the way
- Interpretability: Probes, Features and Circuitsages 23 to 24 · on the way