Statistical ML notes

Topic-by-topic notes on classical statistical and machine learning, from linear regression to neural networks.

1. Part 1Linear regressionSimple and multiple regression, model assessment, categorical predictors, polynomial regression.
2. Part 2ClassificationLogistic regression, generative classifiers, evaluating classifiers.
3. Part 3ResamplingResampling methods and cross-validation.
4. Part 4Model selection and regularisationSelection criteria, ridge regression, lasso.
5. Part 5Dimension reductionPrincipal components regression, partial least squares.
6. Part 6Support vector machinesSupport vector classifier, kernel SVMs.
7. Part 7Unsupervised learningPCA and clustering.
8. Part 8Deep learningNeural networks.