- Joint, Marginal and Conditional Probabilityages 18 to 19 · 18 questions
- Data as a Matrix: Rows, Features and the Targetages 18 to 20 · 15 questions
- Likelihood and the Maximum Likelihood Estimateages 18 to 20 · 8 questions
- Linear Regression by Least Squaresages 19 to 20 · 12 questions
- Bayes' Rule and Updating a Beliefages 18 to 19 · 14 questions
- Training Across Many Devices: Data, Model and Pipeline Parallelismages 23 to 24 · 8 questions
- Serving a Model: Batching, the Key-Value Cache and Quantisationages 23 to 24 · 8 questions
- Gradient Descent: Following the Slope Downhillages 19 to 20 · 8 questions
- Logistic Regression and the Decision Boundaryages 19 to 21 · 16 questions
- Overfitting and the Bias-Variance Trade-offages 19 to 21 · 11 questions
- Regularisation: Charging for Complexityages 20 to 21 · 8 questions
- Cross-Validation and Honest Model Selectionages 20 to 21 · 16 questions
- Beyond Accuracy: Precision, Recall and the Cost of an Errorages 20 to 22 · 8 questions
- Decision Trees and Ensemblesages 20 to 22 · 8 questions
- Clustering: Structure Without Labelsages 20 to 22 · 8 questions
- Principal Components and Dimensionality Reductionages 20 to 22 · 15 questions
- From Perceptron to Multilayer Networkages 21 to 22 · 8 questions
- Backpropagation: Assigning Blame for an Errorages 21 to 22 · 17 questions
- Deep Learning: Convolution, Sequence and Scaleages 21 to 22 · 8 questions
- Attention as a Learned Lookupages 22 to 23 · 8 questions
- The Transformer Block: Heads, Residuals and Normalisationages 22 to 23 · 8 questions
- Tokenisation and What a Model Actually Readsages 22 to 23 · 8 questions
- Pretraining by Predicting the Next Tokenages 22 to 23 · 8 questions
- Scaling Laws and the Compute Budgetages 22 to 23 · 8 questions
- Adapting a Pretrained Model: Fine-Tuning and Low-Rank Updatesages 22 to 24 · 12 questions
- Generative Models: Learning a Distribution You Can Sampleages 22 to 24 · 8 questions
- Diffusion Models: Learning to Undo Noiseages 22 to 24 · 8 questions
- Benchmarks and the Traps in Themages 22 to 24 · 8 questions
- Markov Decision Processes: States, Actions and Returnages 22 to 24 · 11 questions
- Temporal-Difference Learning and Q-Learningages 23 to 24 · 8 questions
- Policy Gradients and the Actor-Critic Splitages 23 to 24 · 8 questions
- Learning from Human Preferences: Reward Models and Policy Optimisationages 23 to 24 · 8 questions
- Fairness, Accountability and the Limits of a Modelages 21 to 22 · 8 questions
- Interpretability: Probes, Features and Circuitsages 23 to 24 · 8 questions