Course Project

An integral part of the course is the class project (32% of the grade), which gives students a chance to apply deep architectures discussed in class to a research oriented project. The students should work in pairs. The course project may involve

• Design of a novel end-to-end approach and its experimental analysis, or
• An extension to a recent study of non-trivial complexity and its experimental analysis.

In preparing your progress and final project reports, you should use the provided LaTeX template and submit them electronically in PDF format. Late submissions will be penalized.

Deliverables

• Proposals (2%): November 13, 2022.
• Project progress reports (6%): December 18, 2022
• Final project presentations (8%): Jan 16,18,23,25 2023
• Final reports (12%): January 29, 2023
• The quality of the contributions/The difficulty of implementation (4%)

Project Proposal

Each group should submit a project proposal (~1-2 page long) on their specific project idea by November 13, 2022. The proposal should be prepared using this LaTeX template and should provide the following:

• The research topic to be investigated,
• A list of key readings.
• Design overview,
• What data and metrics you will use,
• An approximate timeline of activities.

Progress Report

Due: December 18, 2022 (11:59pm)

Each group should submit a project progress report by December 18, 2022. The report should be 4-6 pages and should be prepared using this LaTeX template. In your report, please describe the following points as clearly as possible:

• Abstract. A summary of your project idea and its contributions
• Problem to be addressed. Give a short description of the problem that you will explore. Explain why you find it interesting.
• Related work. Briefly review the major works related to your research topic.
• Methodology to be employed. Describe the main approach that is expected to form the basis of the project. State whether you will extend an existing method or you are going to devise your own approach. Add necessary equations/theorems to formally present the problem and/or your model.
• Experimental evaluation. Briefly explain how you will evaluate your results. State which dataset(s) you will employ in your evaluation.
• Preliminary results. Implement a simple baseline method and report its performance. Include the results of your model (if any).
• Visualization. Include a figure or a diagram that describes an overview of your approach.

Final Report

Due: January 29, 2022 (11:59pm) (No late submissions)

As the last deliverable of the course project, each group is expected to submit a project report prepared using this LaTeX template. The report should be 8 pages and should be structured as a research paper. It will be graded based on clarity of presentation and technical content. A typical organization of a report might follow:

• Title, Author(s).
• Abstract.
• Introduction. This section introduces the problem that you investigated by providing a general motivation and briefly discusses the approach(es) that you explored to solve this problem.
• Related Work. This section discusses relevant literature for your project topic.
• The Approach. This section gives the technical details about your project work. You should describe the representation(s) and the algorithm(s) that you employed or proposed as detailed and specific as possible.
• Experimental Results. This section presents some experiments in which you analyze the performance of the approach(es) you proposed or explored. You should provide a qualitative and/or quantitative analysis, and comment on your findings. You may also demonstrate the limitations of the approach(es).
• Conclusions. This section summarizes all your project work, focusing on the key results you obtained. You may also suggest possible directions for future work.
• Acknowledgements. This section provides information about specific contributions of each team member to the project (see Contributions section of the GPT3 paper as an example). This section does not count within the 8 pages limit.
• References. This section gives a list of all related work you reviewed or used.