Machine Learning
Fall 2009
Distance Learning Section
Department of Computer Science
| |
Machine Learning Fall 2009 Distance Learning Section Department of Computer Science | |
Description: In this class you will learn about a variety of machine learning algorithms for finding patterns in data. The algorithms include techniques from statistics, linear algebra, and artificial intelligence. Students will be required to solve written exercises, implement a number of machine learning algorithms and apply them to sets of data, and hand in written reports describing the results.
For implementations, we will be using R, an open-source environment very similar to S and S-Plus. You may download and install R on your computer, and work through the on-line tutorials at the R web site to help prepare for this course. R provides an interactive interpreter environment that facilitates the incremental development of code. R's built-in matrix operators and graphics functions greatly simplifies the coding of the machine learning algorithms and the visualization of data and results. Past CS545 students have continued using R in other classes and for their own reseach projects.
Class meetings will be a combination of lectures by the instructor, discussions of students' questions, and some presentations by on-campus students. Students taking the Fall 2009 Distance Learning section of CS545 will access video lectures and notes from the on-campus section which will be taught during the same semester. Questions and discussions will take place on an on-line discussion board open to on-campus and distance learning students. The Fall 2009 course will be similar to the Spring 2008 section of CS545.
Instructor: Chuck Anderson is the instructor for this course. He has been an active researcher in machine learning for over 20 years. Many of the topics in the course are closely related to his current research projects and those of other AI researchers in the CSU Department of Computer Science.
Prerequisites: Programming experience with at least two languages, courses or experience in linear algebra and statistics. Experience with programming regression, classification, neural networks, or other adaptive algorithms is helpful background for this class. Send e-mail or call the instructor, Chuck Anderson, to discuss how your experience relates to the requirements for this course.
Textbook: