Skip to content

Latest commit

 

History

History
47 lines (34 loc) · 3.77 KB

project.md

File metadata and controls

47 lines (34 loc) · 3.77 KB
Raw

Project

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)

Agenda

  • Project proposal, due by March 18, 2024.
  • Project code and report, due by May 17, 2024.

Projects should be submitted on Gradescope.

Instructions and evaluation guidelines

  • 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.
  • Towards the end of the class, you will submit a project report (around 8 pages), in the format of a machine learning conference paper which has to include the following sections:
    • Introduction: which states the problem which has been tackled
    • Related Work: which covers research that is related to the considered problem
    • Methods: a clear and detailed description of the neural networks (architecture, training-parameters, loss function, data)
    • Results:
      • qualitative analysis: could include examples of generated images, correct vs wrong predictions, ...
      • quantitative analysis: general overview of final performance, loss curves, comparison table with error-bars, ...
    • Discussion: a critical discussion of the performance of the neural network, analysis of the potential limitations, tips for future work
  • The grade will depend on two main components:
    • quality and originality of the project (are the contributions of the group to the development of the project well defined? what has been implemented with respect to the original research questions, what has been re-used from existing coding directories?)
    • presentation of the project (structure of the report, clarity of figures/tables, correctness of the English language)
  • Both the project proposal and the project report should follow the LaTex template template-report.tex. Feel free to change the structure of the latex template if needed.

Honor code

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.