CS 8803 DMM: Data Management and Machine Learning (Fall 2020)

Project

The main component of the course will be an original research project. Students will organize into groups and choose to implement a project that is (1) relevant to the topics discussed in class, (2) innovative with ideas not tested before, and (3) unique (i.e., two groups may not choose the same project topic). The projects will vary in both scope and topic, but they must satisfy this criteria. Strong projects can eventually lead to a conference paper.

Each project is comprised of 5 deliverables due at different times:

• Project Proposal/Progress Writeup
• Project Proposal/Progress Presentation
• Project Final Report Writeup
• Project Final Codebase
• Project Final Presentation
  

Collaborations:

You are to form project groups of one to three people per project. The technical contribution of 3 people project is expected to be greater. This will be reflected when grading the final project report.

Project Ideas:

You can come up with you own project idea that satisfies the above three criteria, or choose one project from the list of example projects the instructor provides. Either way, you are expected to actively engaged with the instructor on project design.

Grading (50% of total score):

• Project Proposal Writeup: 10%
  
• Project Proposal/Progress Presentation: 10%
  
• Project Final Report: 15%
  
• Project Final Codebase: 5%
  
• Project Presentation: 10%
  

Grading: Project Proposal

The proposal will be evaluated on a 100-points scale

• Problem Motivation and Definition: 30 points
• Related Previous Work: 30 points
  
• Intended Direction of Research: 20 points
  
• Evaluation Plan: 20 points

 

Grading: Project Final Report

The final report will be evaluated on a 100-points scale

• Technical Contribution: 50 points
• Experimental Evaluation: 30 points
  
• Writing Clarity: 20 points

Grading: Project Presentation

The final report will be evaluated on a 100-points scale

• Clarity: 80 points
  
• Organization: 20 points