9.11 Other ML methods: Quick overview

• Given time we focused on classification/logistic regression (James et al. 2013, Ch. 2/4/5) (skipped LDA and QLDA)
• Quick overview of other content of James et al. (2013)
  • Linear regression (James et al. 2013, Ch. 3)
  • Linear model selection and regularization (James et al. 2013, Ch. 6)
    • Enhance least squares with other methods (subset selection, shrinkage/regularization, dimension reduction)
  • Moving beyond linearity (James et al. 2013, Ch. 7)
    • Polynomial regression, step functions, regression splines etc.
• Tree-based methods (James et al. 2013, Ch. 8)
  • Used both for regression and classification; Involves segmenting predictor space into a number of simple regions (using splitting rules)

• Support Vector Machines (James et al. 2013, Ch. 9)

• Unsupervised learning (James et al. 2013, Ch. 10)

References

James, Gareth, Daniela Witten, Trevor Hastie, and Robert Tibshirani. 2013. An Introduction to Statistical Learning: With Applications in R. Springer Texts in Statistics. Springer.