ECE 543: Coursework
Your final grade in ECE 543 will be determined according to the following revised point weighting formula:
- written problem sets:
two one ninety-minute midterm exam: 20% each 20%
- final project:
Written problem sets:
Format and submission instructions.
- For the project, you are to choose a topic related to the course content, and understand and critically evaluate two or three major papers in that area. Then demonstrate knowledge of the papers by working an example based on a paper or possibly extending the theory of a paper. You will need to write a project report of five to ten pages in length, and prepare a fifteen-minute presentation. You may work in groups of up to three students.
- Good sources of recent papers (there are others, of course):
Proceedings of Machine Learning Research, includes papers from major conferences, such as COLT, ICML, ALT, AISTATS
Proceedings of NIPS
- By Thursday, March 29, I would like to receive a brief project proposal from each group or individual (brief = no more than a couple of paragraphs).
- The date/time of the final exam for ECE 543 is Friday, May 4, 8am -- 11am. Assuming there are no more than 12 groups, we should be able to wrap up all the presentations in that time.
- The written reports will be due by the end of the finals week, submission via Compass.
All homework must be typeset using LaTeX (if you do not know LaTeX yet, now is as good a time as any to learn it -- you will need it in grad school anyway) and compiled into a pdf file. The files will be submitted through Compass 2g. Upload instructions:
Multiple attempts will be allowed, but only your last submission before the deadline will be graded.
We reserve the right to take off points for not following directions.
- Log into https://compass2g.illinois.edu and go to Spring 2018 - ECE 543 Statistical Learning Theory - Section C.
- Select Course Content from the left column.
- Select Homework X (where X is the number of the current assignment) from the list, and follow the instructions.
- Upload your pdf file as an attachment.
- Hit Submit.
Late policy: No late submissions will be accepted.
If you have a compelling reason for not being able to submit the assignment on time
and would like to make a special arrangement, you must send me email at least a week before the due date
(any genuine emergency situations will be handled on an individual basis).
Academic integrity: Feel free to discuss the assignment with each other in general terms,
and to search the Web for general guidance (not for complete solutions). All solutions should be written up
individually. If you make substantial use of some information from outside sources,
be sure to acknowledge the sources in your solution. At the first instance of cheating (copying from other students or unacknowledged sources on the Web), a grade of zero will be given for the assignment. At the second instance, you will automatically receive an F for the entire course.