What concepts or methods from the machine learning field interest you the most? This final assignment is your chance to explore these interests. Projects can include:

• Exploring variants of an algorithm studied in class or an algorithm not studied in class. Such a project would compare the performance of the algorithms across a number of datasets to some baseline methods (datasets taken e.g. from the UCI ML repository).
• Duplicating a result reported in a publication.
• Applying ML techniques to a dataset that you have personal interest in.

A few more details:

• You are required to work in pairs for the project. Three member teams will be allowed, but the need for the team should be justified and approved by the instructor. One report is submitted per team. Clearly define what the responsibility of each team member.
• Your project needs to demonstrate you have learned something new about machine learning. It needs to be of a sufficient level of difficulty, so make sure to check in with the instructor before submitting your project proposal. Applying some of the algorithms you learned in class to a few UCI datasets is not good enough!

Submit via Canvas a proposal by Nov 3rd describing

• the machine learning problem/algorithm that you are planning on addressing in the project
• the steps you will take to investigate it
• who is on your team,
• what each team member will do, and
• a list of at least four key steps your team will complete and the dates by when they will be completed.

Only one person from your team should submit the proposal via Canvas. Proposals are limited to two pages.

Submit via Canvas the PDF file of your written report by midnight December 12th. Your report must clearly describe what each team member did; all members of the team need to participate in the writing.

The recommended structure of the report should include:

• Title
• Abstract
• Introduction (incl. problem statement, motivation for the work, review of previous work, open questions in the domain, and how you are proposing to address them)
• Methods. Make sure to give a detailed enough description of new algorithms that were not covered in class.
• Results and Discussion
• Conclusions and Future Work
• References

Only one person from your team should submit the final report. In grading, each team member's contribution will be taken into account. You may submit a Jupyter notebook as a demo of your project.

We will have a poster session 2:30-4:30pm on December 7th, in which the on-campus students will present their projects. This is only for students in the on-campus section.

Posters are one of the primary ways of communicating research: every scientific conference has a poster session, and learning how to create good posters and present them well is an important skill for a graduate student. A few poster-related resources:

• A nice presentation with useful advice on making an effective poster (most of which I agree with).
• An article in the journal Nature on scientific posters.
• A blog dedicated to the art of making better posters.

Here is what the grade sheet will look like for this assignment.

CS545 Final Assignment

======================================================================
Proposal:  10 points

  (4 points): The project is well-motivated (why are doing this).
  (4 points): Description of the tasks involved (what will you be doing).
  (2 points): Timeline for carrying out the project and clear team member 
  responsibilities (who will do what and when).

======================================================================
Poster:  25 points (on-campus students)

  (9 points): The poster succinctly and clearly explains what you did
  (8 points): The poster was well laid out and makes good use of visual aids
  (8 points): The poster was well presented by the team, demonstrating good 
  understanding of the material and ability to answer questions.

======================================================================
Video presentation:  25 points (online students)

  (9 points): The video succinctly and clearly explains what you did
  (8 points): The video makes good use of the technology and is well delivered
  by the team.
  (8 points): The video demonstrates good understanding of the material.

======================================================================
Written Report:  65 points

  (10 points): Good introduction and motivation for the project.
  (15 points): Clear description of what you did and how you did it.
  (15 points): Results are clearly presented and discussed in depth.
  (10 points): Project is sufficiently challenging.

  Points will be taken off for poor grammar/spelling and failure to follow 
  instructions on length and structure.