CMPUT466- Final project Solved

Objectives:

[10 marks] The basic goal of the mini-project is for the student to gain first-hand experience in formulating a task as a machine learning problem and have a rigorous practice of applying machine learning algorithms.
[5 marks] The second goal (optional to undergrads) is to accomplish a non-trivial machine learning project, such as replicating a recent top-tier machine learning publication (published at ICML, NeurIPS, ICLR, etc.), proposing new models, and empirically analyzing machine learning models in a significant way.
Replicating a paper published at an unknown or non-machine learning venue may not constitute a non-trivial project.

The 5 marks count as bonus for undergrads but are included within 100 total marks for grads.

Team work

Collaboration of the course project is possible only if

all team members have already had first-hand experience,
they intend to do a non-trivial project, and
the team must have no more than three members.
 

If teamwork is approved, the team members (name, ID, and email) and individual contributions must be stated clearly in all submissions. All team members must upload the submissions to their own eClass assignments.

A non-trivial project requires significantly more time than a project satisfying basic requirements only, so a significant amount of time has to be set for the project.

The student must decide early if he/she is going to do a non-trivial project. If so, the student must send a notice of intent (NOI) by Sep 18, indicating a title, a short description, and team members. The NOI will not be reviewed but is mandatory for a non-trivial project.

The instructor offers a chat to anyone who sends a NOI. The chat can be done during office hours or by appointment initiated by the student. The instructor’s availability can be found here: https://lili-mou.github.io/calendar.html

The student is supposed to read literature and prepare experimental environments after NOI. By the proposal deadline, the student must submit a pdf proposal to eClass. The instructor will read the proposal and make a comment, especially on how non-trivial the proposal is. The instructor offers another chat to those who submit the proposal.

Notice that an intended non-trivial project may not get all 15 marks or, if not satisfying the basic requirements, may not get 10 marks.

Basic Requirements [10 marks]:

Formulating a task into a machine learning problem. The student CANNOT re-use any task in coding assignments (namely, house price and MNIST datasets) as the course project.
Implementing a training-validation-test infrastructure, with a systematic way of hyperparameter tuning. The meaning of “training,” “validation,” “test,” and “hyperparameter” will be clear very soon.
Comparing at least three machine learning algorithms. In addition, include a trivial baseline (if possible). For example, a majority guess for k-category classification yields 1/k  The machine learning algorithms must be reasonable for solving the task, and differ in some way
(e.g., having different hyperparameters do not count as different machine learning algorithms).

Requirements for a non-trivial project [5 marks]:

A non-trivial project could be either replicating a recent machine learning paper that involves some sophistication, proposing new models, or conducting empirically analyzing machine learning models in a significant way.

Typically, a non-trivial project involves a significant amount of literature reading, programming and conducting experiments. A student would not expect any bonus mark by trying some CNN/RNN models, or applying existing code base to a new task in a straightforward way. If a student seeks non-triviality marks by replicating a recent paper, the student should assume

Tips

Using external general-purpose machine learning packages is allowed but should be acknowledged (e.g., use libsvm to solve the task by a few lines of function call). However, using a code base directly related to your task is not allowed (e.g., download a GitHub repo and only write a few lines of script like “sh run.sh”).
There is no constraint on the number of pages of the course report. However, the length should reflect the substance of the project, and in a normal case, a few pages suffice. An over-lengthed report will not yield a higher mark. On the contrary, it shows poor presentation skills (and may lead to mark deduction).