The course project is an opportunity for you to apply what you have learned in class to a problem of your interest. You can consider any kind of project which has to be solved via any deep learning method. We recommend you to tackle the problem from a very applicative perspective where you should focus on building and training a deep neural network from scratch.
Some general potential problems could be the following:
- Computer vision applications (classification, object detection, segmentation)
- Natural language processing applications (machine translation, image captioning, recommendation systems)
- Conditional generative models (image synthesis, style transfer, text generation)
- Deep reinforcement learning (video games, robotics)
- Project proposal, due by March 29, 2026.
- Project code and poster, due by May 15, 2026.
Projects should be submitted on Gradescope.
- Students can work in groups of maximum 3 students.
- Each group must write a short (1-2 pages) research project proposal. It should include a description of a minimum viable project, the data you will use or collect, the computing resources you think you will need, some nice-to-haves if time allows, and a short review of related work. Project proposals must be approved before working on the project. They should follow the LaTex template
template-report.tex. - At the end of their project, each group must create a poster motivating their idea and describing their results, in a poster format typical of a Machine Learning conference (see the template folder). The poster may include the following sections:
- Abstract: a short summary of your project
- Introduction - Problem Statement: stating the problem which has been tackled
- Methodology: a description of your dataset, neural network architecture, training procedure (pictorially if possible)
- Results: qualitative (e.g. examples of generated images, segmentation boxes…) and quantitative (overview of final performances with metrics, loss curves, etc.)
Note: Your poster is NOT a report: select the most important information and avoid overcrowding it with text. A visual poster is always more appealing and interactive. You can obviously modify the template to your liking, or even choose not to follow it.
- A poster presentation session will be held at the end of the course (May 15, 2026), where students will have to present their project and answer practical questions justifying their choices, discuss their results, etc.
- The grade will depend on two main components:
- Quality and originality of the project (Are the group's contributions to the project development well defined? What has been implemented with respect to the original research questions? What has been reused from existing code repositories?)
- Presentation of the project (poster structure, clarity of figures/tables, quality of the presentation and answers to questions)
You may consult papers, books, online references, or publicly available implementations for ideas that you may want to adapt and incorporate into your project, so long as you clearly cite your sources in your code and your writeup. However, under no circumstances, may you base your project on someone else's implementation. One of the main learning outcomes of this project is indeed for you to gain experience in designing and implementing a deep learning system by yourself.
If you are combining your course project with the project from another class, you must receive permission from the instructors, and clearly explain in the proposal, final report the exact portion of the project that is being counted for INFO8010. In this case you must prepare separate reports for each course, and submit your final report for the other course as well.
Credits: Project instructions partly adapted from Stanford CS231n.