EEE 450--- Introduction to Machine Learning

Izmir Katip Çelebi University, Faculty of Engineering and Architecture

Fall 2019

Course Project

Your first task is to pick a project topic. If you're looking for project ideas, please come to project office hours, and we'd be happy to brainstorm and suggest some project ideas.

Some Project Ideas:

Notes on a few specific types of projects:

  • Deep learning projects: Since EEE450 discusses many other concepts besides deep learning, we ask that if you decide to work on a deep learning project, please make sure that you use other material you learned in the class as well. For example, you might set up logistic regression and SVM baselines, or do some data analysis using the unsupervised methods covered in class. We may grade these projects using different criteria to make sure that grading is fair for students who have not had exposure to DL before. Finally, training deep learning models can be very time consuming, so make sure you have the necessary compute.
  • Preprocessed datasets: While we don't want you to have to spend much time collecting raw data, the process of inspecting and visualizing the data, trying out different types of preprocessing, and doing error analysis is often an important part of machine learning. Hence if you choose to use preprepared datasets (e.g. from Kaggle, the UCI machine learning repository, etc.) we encourage you to do some data exploration and analysis to get familiar with the problem.
  • Replicating results: Replicating the results in a paper can be a good way to learn. However, we ask that instead of just replicating a paper, also try using the technique on another application, or do some analysis of how each component of the model contributes to final performance.

Project Presentations

  • The class projects will be presented at the last two week of term. Please prepare a brief power point presentation (15-20 minutes) about your project. At the presentation session, you'll also have an opportunity to see what everyone else did for their projects.


Project FAQs


1. What are the deliverables as part of the term project?

The project has four deliverables:

  • Proposal  (Due Date: 31/10/2019)
  • Implementations (Due Date: 18/12/2019)
  • Presentation (19/12/2019)
  • Final Report (Due Date: 18/12/2019)


2. Should final project use only methods taught in classroom?

No, we don't restrict you to only use methods/topics/problems taught in class. That said, you can always consult the instructor you are unsure about any method or problem statement.


3. Is it okay to use a dataset that is not public ?

We don't mind you using a dataset that is not public, as long as you have the required permissions to use it. We don't require you to share the dataset either as long as you can accurately describe it in the Final Report.


4. Is it okay to combine the EEE450 term project with that of another class ?

No, it has not been allowed.


5. What are acceptable team sizes and how does grading differ as a function of the team size ?

We recommend teams of 2 students, while teams sizes of 1 or 3 may be also acceptable. The team size will be taken under consideration when evaluating the scope of the project in breadth and depth, meaning that a three-person team is expected to accomplish more than a one-person team would.


6. Do I have to be on campus to submit the final report?

No, the final report will be submitted via email to by the deadline.


7. What fraction of the final grade is the project?

The term project is 20% of the final grade.


8. What is the late day policy for group project?

Each of the team members must use one late day if they wish to extend the deadline by a day. Late days cannot be used for the final project presentation or final report.


9: Can we use some Machine Learning libraries such as scikit-learn or are we expected to implement them from scratch?

You can use any library for the project.


10: Is it ok to use a public repository for version control?

A private repository is recommended (and free with GitHub's Education Pack), but a public repository is also okay.


11: What if two teams end up working on the same project?

It is okay if two teams end up working on the same project as long as they don’t coordinate to do so, in order to not be biased in the way they tackle the problem. Alternatively the teams can coordinate to make sure they work on different problems.


12: Are we required to use Python for the project?

Any programming language is allowed for the project.


[Final Report Submission Template]