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 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.
Each student is required to participate in class by submitting brief critiques of selected papers to be covered in class and participating in class discussions. The purpose of the critiques is to stimulate critical thinking and discussions on class topics. A critique is not merely a summary, but your own reactions to the content of the reading. Critiques should be approximately one page of single spaced type.
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.
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. Students are required to obtain approval on a project proposal. Ideas for projects will be distributed in class.
All work in this course is to be done individually, without assistance from others, except from the instructor and teaching assistant. Students may use internet resources, but must cite sources.