COS424/SML302: Fundamentals of Machine Learning

Princeton University
Spring, 2019

Administrative To Do

• Sign up on Piazza
• Take the seven minute survey! We will use these data in our in-class examples.

Course Materials

Resources

• Python coding and machine learning:
  • sci-kit learn includes many python packages for a large range of machine learning methods and models.
  • The iPython notebook is a simple data analysis tool for working with data in a reproducible way.
  
  
• Here are some resources for learning and using R if you care to use R in visualization (project code is expected to be in Python):
  • Download R at the R Project for Statistical Computing.
  • Start to learn R by reading Introductory Statistics with R by Peter Dalgaard (Ch 1-2).
  • Many people like R studio.
  • Some people use Emacs Speaks Statistics.
  • Consider using ggplot2 for beautiful graphics and figures.
  • Consider using KNITR for reproducible R pipelines.
  
  
• Additional books and reading that you might find useful (Murphy book PDF link is on the Piazza page):
  • The Hastie et al. book, Elements of Statistical Learning can be found here.
  • Michael Lavine, Introduction to Statistical Thought (an introductory statistical textbook with plenty of R examples, and it's online too)
  • David J.C. MacKay Information Theory, Inference, and Learning Algorithms (PDF available online)
  • Chris Bishop, Pattern Recognition and Machine Learning
  • Daphne Koller & Nir Friedman, Probabilistic Graphical Models