In the assignments (and lab exercises), you will implement (and experiment) a few widely used machine learning algorithms.

• There are two mandatory and one optional assignments in this course. Each assignment will be released/accessible after the related lectures have been delivered.
• Groups of three (ideally) students will work on assignments together. It is essential that every group member plays an active role, including in writing codes AND in writing the report. A division of tasks based on handing the role of report writing to one person and code writing to another is strongly discouraged!
• Be creative with experiments; try different scenarios and discuss the pros and cons.
• Your report needs to include a brief description of how the tasks were distributed among the team members. This is used to differentiate individual grades (see here for an example of the report). Note that this is not a template for report and feel free to use your own format (LaTex is recommended).
• You may submit an assignment multiple times, but it is mainly assessed based on your first submission. If you improve and resubmit your assignment based on feedback (from the teachers or peer-reviewing), you may receive a slightly higher mark (but no more than 0.5).
• Strict deadline: 10% deduction per day late, no more accepted after 3 days.

Read the assignment instruction carefully before you start!

The assignment materials are available on BrightSpace under the "Assignments" tab. After you complete an assignment, submit it to BrightSpace (for the university to have a permanent record or your work).

Copyright @Liangliang Nan. 2022