Projects

Practical work is an essential part of learning. We offer you an opportunity to test your newly acquired machine learning skills against real-life problems. Please read this page carefully before asking questions (for questions use #questions-ml25 channel in Slack).

Key dates:

• Team formation (team size is 3 - 4 students), until September 28
• Project plan, deadline October 12 (2 points out of 25 points)
• Intermediate presentations November 17 - 19 (5 points out of 25 points)
• Final presentations and team evaluation December 15 - 17 (15 + 3 points out of 25 points)

Choosing a project

The first step is to find a project that is aligned with your interests. Below are several options:

From the partners:

Read carefully a list of projects proposed by our partners from this document. When choosing a project from a partner, consider not only the topic and the description of an idea, but also if the data is readily available and if the project's complexity is reasonable and aligns well with your expectations. You take full responsibility for working on this project, so be mindful. Also, when you sign up for a project from the partner, make sure that your team does not exceed the limit on the number of teams that they are willing to supervise (this is indicated in the separate field). If you choose a project from one of the partners, connect with a representative person who has proposed a project to get data and guidance. Note that extra time and care must be invested in communicating with a project owner and meeting their expectations. Project owners will be invited to the final presentations and given an opportunity to provide feedback that will be considered in the final assessment.

From Kaggle.com:

You can do a project by participating in one of the Kaggle.com competitions (e.g. Machine Unlearning or Intracranial Aneurysm Detection) or working on some Kaggle dataset (e.g. solar power generation dataset). Kaggle challenges and the datasets are usually supported by 'kernels' where people document and publish their analysis code. You must declare all kernels that you use in your project and convince instructors (during presentations) that what you have done is different from the existing solutions and constitutes a sufficient amount of work worth 25 points.

Come up with a project yourself:

If neither option above is of interest to you, feel free to propose your own project. For example, you may decide to analyze some publicly available data (from here, here, here, here, or here). Make sure there is a very explicit machine learning component in your project - you can consult with instructors if in doubt. If you already have a team, describe your project and the team in the project document. If you don’t have a team, you can advertise your project in Slack in the #introductions channel and try to attract team members.

Team formation (deadline: September 28)

After you have chosen a project (or come up with it yourself), you need to assemble a team or join the existing one. You can either advertise your project in the #introductions channel or comment on someone else's post, letting them know you want to join. Remember: team size must be 3–4 people. If someone has already formed a team, get their approval before adding your name to the existing team in the project document. By the deadline on September 28 at 23:59 - Each team must add their project by specifying the name, project type (from partners, kaggle, or your own), project description, and team members into the project document. Please, this is an obligatory step to continue working on the project! Follow the template in the beginning and check out our example project. If you plan to work on a partner project, please, in the project name section, specify the project identifier (e.g., P1 - NMR prediction and the influence of 3D structures). Also specify which day (Monday, Tuesday, or Wednesday) you want to make your intermediate and final presentation. This would determine which practice session instructors will be grading your presentations.

Project plan: Oct 12 (2 points out of 25 points)

Fill in and submit the project plan by copying the provided project plan template. As said in the file, we recommend taking enough time to get to know the data and the problem domain before writing it up, so plan time for some research before finalizing this. We also recommend reading (or asking ChatGPT) the main principles of managing your team and time, e.g., regular weekly meetings should be a must, dividing clear tasks, checking what is done, and planning every week. These activities also take time and energy, but help to keep the project on track. We provide you with a very simple project management spreadsheet that you can copy to yourself (and modify in any way) to keep track of your progress and plans, it would be good to fill this every week (not graded, but we really encourage this). Or you can make your own or use any other tool.

Intermediate presentation: Nov 17 - 19 (5 points out of 25 points)

The order of presentations will be published later. General guidelines for intermediate presentations:

• Please, do all attend the presentation; if one person is presenting, the rest of the team should support in QA. There is a possibility to present online.
• Make sure to fit your presentation into 5 minutes (with slides), if you go over time, we will penalise your team.
• Add your Google Slides to the corresponding Google folder: TBA for Monday, TBA for Tuesday, and TBA for Wednesday.
• In the presentation, make sure to introduce your team and project owner (if applicable);
• briefly describe the problem you are trying to solve (say why it needs to be solved);
• mention the progress you have made so far;
• tell about your blockers/problems;
• Please specify who in your team is responsible for which part of the work;
• Lastly, say a few words about future steps (what you will accomplish for the final presentation).

Intermediate presentations are compulsory to proceed to the final presentations!

Final presentation: Dec 15 - 17 (15 points out of 25 points)

• Please, do all attend the presentation, if one person is presenting the rest of the team should support in QA. There is a possibility to present online.
• As with the intermediate presentations, the final presentations will be held offline (+ Zoom if needed) with at least two instructors grading the presentations.
• You have up to 5 minutes to make the final presentation.
• Add your Google Slides to the corresponding Google folder: TBA..
• In the presentation, make sure to introduce your team and project owner (if applicable);
• briefly remind us of the problem you are trying to solve (say why it needs to be solved);
• explain what was your approach to the problem (your methods);
• detail the results you have obtained and how they match the initial expectations;
• Please specify who in your team is responsible for which part of the work.
• Lastly, describe a few lessons you learned while working on the project.

Add a link to your repository to your presentation. If you have a private repository, give access to the course instructors. The order of teams and the schedule are the same as for the intermediate presentations (TBA).

Team evaluation: Dec 15 - 17 (3 points out of 25 points)

After you have finished the project and done the final presentation, you need to fill in a questionnaire about each of your teammates separately. This will involve questions about the teammate's contribution. Mostly in terms of whether the person did what they promised to do, attended meetings, etc. Your score will be combined by averaging the scores that your teammates give you, so it can be different for every member of the group.

Grading

Your grade will be composed of the project plan grade (2 points), intermediate presentation (5 points), final presentation (15 points), and the team evaluation (3 points). The presentations will be graded based on roughly the following criteria:

• amount and complexity of work performed (40%),
• quality of presentation (30%),
• degree to which you have completed the initial task (25%),
• being on time (5%).

Project plan and presentation points are assigned to each team member equally unless there is a good reason to believe that some team members have done significantly less or more work than others. Both intermediate and final presentations are to be done during practice sessions (exceptions could be Monday presentations). Each project will be graded by at least two instructors independently, the final grade will be their average. There is no written report for the project. The only thing we will ask you to submit is a link to your project GitHub and presentation.

Short summary of what you have to do:

1. Choose a project a) from a partner b) from Kaggle.com or c) come up with a project idea yourself.
2. By September 28, form a team (3 - 4 people including you) using Slack channel #introductions or your contacts in the course and describe your project + team here.
3. By October 12, submit your project plan (the template is here).
4. Deliver an intermediate presentation on the week of Nov 17 - 19 during a chosen practice session (either on Monday, Tuesday or Wednesday).
5. Deliver a final presentation on Dec 15 - 17 during your chosen practice session.
6. Fill out the team evaluation questionnaire after you are done with the final presentation.

The rest of the information will appear here shortly.