CS 4033/5033 Machine Learning

Course Information

• Required Books
  • Elements of Statistical Learning by Hastie, Tibshirani, and Friedman. Note that this book is available online for free (download the latest copy, currently the 12th printing) or you can order a printed copy via Amazon or Springer.
  • Reinforcement Learning: An Introduction by Sutton & Barto (available online for free)
    • Note we will be using a draft copy of the 2nd edition, which is available at the above link.
  • We will also make use of additional online books, papers, and other resources.
• Optional but potentially useful books:
  • Machine Learning by Tom Mitchell. There is an online version that is more affordable than the hard-cover, created for us by the publisher. Go here to order it.
  • Hands-On Machine Learning with Scikit-Learn and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems by Geron. If you want to do tensorflow stuff with your projects, this may be a useful resource.
  • To dive deeper into deep learning:
    • Deep Learning
    • Neural networks and deep learning
    • Deep learning with Python and the associated jupyter notebooks
• The course syllabus is here.
• Additional information, discussion boards, and announcements will be available on Canvas.
• Class schedule (updated as the semester progresses)

Project Resources

• Coming up with a project (note that the suggested ideas change each year and previous ideas can be useful as well! Plus you are free to come up with your own!):
  • My list of suggested projects for 2018
  • My list of suggested projects for 2017
  • My list of suggested projects for 2016
  • My list of suggested projects for 2015
  • My list of suggested projects for 2014
  • My list of suggested projects for 2012
  • My list of suggested projects for 2011
  • My list of suggested projects for 2010
  • My list of suggested projects for 2009
  • My list of suggested projects for 2008
  • My list of suggested projects for 2007
  • My list of suggested projects for 2006
  • My list of suggested projects for 2005
  • Ray Mooney's list of suggested projects (for his ML class at UT)
  • A sample of final project reports from Fall 2005 (No, you can't repeat a project but this tells you the scope of previous projects)
  • A sample of final project reports from Fall 2006
  • A sample of final project reports from Fall 2007
  • A sample of final project reports from Fall 2008
  • A sample of final project reports from Fall 2009
  • A sample of final project reports from Fall 2010
• Finding related research:
  • Journal of Machine Learning Research (papers available for free)
  • Machine Learning Journal (expensive but some articles available for free)
  • International Conference on Machine learning (2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010, 2011, ... google for other years, papers are generally available for free, try citeseer or google scholar searches to find them)
  • Association for the Advancement of Artificial Intelligence holds an annual conference and the past list can be found here
  • Journal of Artificial Intelligence Research (papers available for free)
  • Citeseer (online paper search engine) and Google Scholar (ditto)
• Acquiring data (if the source is not already specified from your project):
  • Machine Learning datasets available at the ML repository at UCI
  • Write your own simulator
  • Use the hardware
• Designing your experiments:
  • Rob Holte's slides on experiment design
  • Tom Dietterich and Marie desJardins' slides on experiment design
• Writing it up:
  • Ray Mooney's hints on how to write a ML project final report
  • A sample of final project reports from Fall 2005
  • A sample of final project reports from Fall 2006
  • A sample of final project reports from Fall 2007
  • A sample of final project reports from Fall 2008
  • A sample of final project reports from Fall 2009
  • A sample of final project reports from Fall 2010

This page written by amcgovern [at] ou.edu.

Last updated: August 15, 2018 1:08 PM