Project Information
The project is required for all students enrolled in CS686 and is
optional for undergraduate students enrolled in CS486.
- Pick an application domain that interests you.
- Identify a problem in that application domain.
- Analyze or develop new (artificial intelligence) techniques to tackle this problem.
- Optional: Implement and evaluate empirically some of those techniques
- Undergraduate students can form terms of up to 3 people, but graduate students must do the project by themselves
There are two parts to the project: the proposal and the final report.
Proposal (No Marks)
The proposal is due by November 1, 2017. It should be at most one page and contain the following information.
- Names of team members (for undergraduate students only)
- What is the application domain
- What is the problem you plan to tackle
- Cite 6-10 papers that you plan to survey concerning this problem
- What (artificial intelligence) techniques do you plan to develop or analyze
The proposal should be submitted via the Project Proposal Dropbox on Learn.
Report (20% of final mark for CS686 and 5% bonus for CS486)
The final report is due on the last day of classes. However, we will accept project up until the date of the final exam without penalty. It should be at most 8 pages in length and should explain the big picture and any necessary detail.
Projects should be submitted via the Project Dropbox on Learn.
Suggested Structure for the Report
- Introduction
- What is the application domain?
- What is the problem?
- Techniques to tackle the problem
- Brief survey of previous work concerning this problem (i.e. the 6-10 papers that your read)
- Brief description of any other relevant techniques
- Analysis of techniques
- Comparison: advantages/disadvantages, scalability, ease of use, etc
- Optional: Report on your empirical evaluation
- Conclusion
- What is the best technique?
- Can we solve the problem today?
- What future research do you recommend?
Format
Use the Association for the Advancement of Artificial Intelligence (AAAI) formatting files (
http://aaai.org/Publications/Author/author.php). These will produce a 2 column report. Your report should be no more than 8 pages long, including references.
Resources
Many of the AI conferences and journals post their proceedings online so that they are accessible for everyone (and the few that do not will be accessible if you are on campus or using the library proxy).
Some resources that you might find useful include
- Association for the Advancement of Artificial Intelligence (AAAI)
- International Joint Conference on Artificial Intelligence (IJCAI)
- NIPS
- International Conference on Machine Learning (ICML)
- International Conference on Autonomous Agents and Multiagent Systems
- Association for Computational Linguistics
- ACM Special Interest Group on Artificial Intelligence (SIGAI)
- Journal of Artificial Intelligence Research
- Artificial Intelligence (journal)
Note that this list is far from complete and there are many other relevant conferences and journals that you can consult.
Questions
If you have any questions, or are stuck for a project idea then please contact the instructors. We love chatting about research ideas.