Poster Guidelines

Instructions for posters apply only to Pit students who will be presenting posters. The scoring rubric remains the same for SV/Doha/Kigali students.


PDF versions of the poster need to be submitted on Canvas by May 4th, 11.59pm. Only one submission per team.

Poster Sessions

Students are required to attend the poster sessions. You will need to present your poster and review other posters. Since grading is by crowd sourcing, your reviews are important. If you cannot attend, please post on piazza under the “Poster Session Conflict” with your name, andrewid and an explanation of the conflict.

Important Information

Poster Printing

Presentation and Grading (MLP)

Every team should be prepared to demonstrate your project to the graders who will review the posters in a random order. All of your team members need to present your work.

We disclose some grading criteria as follows:

  1. Problem: whether the problem description is clear? Is the motivation strong? And is the problem nontrivial? (10 pts)
  2. Details of the proposed methods: clear enough? Technically sound? Originality? (10pts)
  3. Completeness: Is your work complete? Have you obtined results consistent with successful completion of the work? (10pts)
  4. Results: are the results reasonable? how do you set up their experiments? Comparisons with others? Can you explain the results? Have you looked into the results and gained some insights on DL models/algorithms? (10 pts)
  5. Publishability: Is your work potentially publishable? (10 pts)

Poster is suggested to include

  1. Clarity of poster: Create clear sections in your poster considering the following points. Please do not fill the poster with text, summarize ideas and consider using figures and tables.
  2. Introduction: What are you trying to solve? Why is it important?
  3. Related work: Previous work related to your topic that served as a baseline or motivation.
  4. Methods: Which techniques did you apply? You are strongly encourage to add an illustration of your Machine Learning pipeline. (suggested: figures)
  5. Dataset: Summary of the description of dataset, number of files, train and test partitions, labels, etc. (suggested: tables)
  6. Results: Your experimental results. What metrics did you use for evaluation? How do your results compare to prior work or your baseline? (suggested: figures or tables)
  7. Conclusions: Include a summary of and be ready to discuss the following aspects: Analyze your model and results. Describe how the current results in each of the experiments align with your expectations. Highlight a few limitations of your approach (e.g., strong assumptions you had to make, constraints, when your method didn’t work in practice, etc.). Do the results and the explanation provide insights into the ML models or the dataset that you were dealing with? Comment on whether you think there is a way to further improve your method to eliminate these limitations.
  8. References and citations: Add the most relevant citations only.