CptS 570 Fall 2007 - Machine Learning

Course Details


The purpose of this course is to expose the student to several machine learning paradigms and provide in-depth understanding of selected methods.


Readings will be taken primarily from Mitchell's textbook on "Machine Learning." Some readings will be taken from individual papers. The readings will be posted on the course website. Students are expected to have completed the required readings by the beginning of class for which they are assigned.


Students will be required to complete several homework assignments. Homeworks will provide hands-on experience with selected learning methods and will test the student's understanding of topics discussed in class. Coding will be required.


Students will be required to complete two in-class exams. Exams will test the student's understanding of the concepts discussed in class and performed on the homeworks.


Each student will make a class presentation on one or more technical papers in the area of machine learning to be approved by the instructor. The presentation must demonstrate an indepth understanding of the topic, including background material from the paper's references, and provide a critical review. Longer papers tend to be more self-contained; whereas, shorter papers will require more auxiliary material.


The class project serves to further the student's understanding of one or more methods through an experimental or theoretical analysis of the learning methods. Details on the class project will be distributed in class.


Students will submit critiques on selected papers. A critique is not a summary of the paper, nor an assessment of the writing style, but the student's critical assessment of the main points of the paper. Critiques should be approximately one page, single spaced. About one-third to one-half of the critique should summarize the main points of the paper. Next, the student should provide their opinions on these points, whether the conclusions are convincing, and why or why not. Finally, the critique should discuss the student's own conclusions about the topics of the paper, e.g., are there better ways to address the same issues, and how they relate to other topics discussed in the course.

Class Participation

Students are expected to attend all classes and actively participate in discussions.

Academic Integrity

All work in this course is to be done individually, without assistance from others, except from the instructor and teaching assistant. No portion of your work may be copied from other sources, including the internet.