Poster Presentations

Most computer science conferences include a poster session where presenters stand beside large-format posters that summarize research results. Conference attendees then have the opportunity to sip tasty beverages while circulating among the posters and talking to the presenters about their work.

The goal of our poster session is to give you a chance to research some area of AI that interests you, and to present what you have learned to the rest of the class. I'll be flexible about the topics of the posters. Possibilities include:

• An AI application area.
• An AI Algorithm that we did not get a chance to cover in detail.
• An AI project that you are proposing - possibly with the first steps completed.

Your topic should be narrow enough for you to present it in some depth. Your poster should be visually appealing, include appropriate figures, and be technically accurate. Your poster should include references to peer-reviewed papers.

There will be three deadlines for this project:

• Deadline 1: Topic proposal.
• Deadline 2: Annotated bibliography.
• Deadline 3: Poster presentation.

Topic Proposal

For this deadline you should submit a short (1-2 paragraph) description of your topic, along with at least one representative reference.

Annotated Bibliography

Your annotated bibliography must include at least six peer-reviewed conference or journal papers. At least three of these papers must contain a reference to some other paper in your bibliography. For each paper, you must provide complete bibliographic information as well as a brief summary of the paper. The summary should describe the key results, note any references to other papers in your bibliography, and explain the connection to those referenced papers.

Poster

Exact formatting requirements TBD.

Finding Papers

Here are some possible starting points for finding high quality papers.

Google Scholar is probably your best starting point. A good way to get started is do some keyword searches related to your topic and take a look at the most highly cited papers that appear relevant. There are many low-quality or uninteresting papers out there. Citation counts provide a good mechanism for focusing attention on noteworthy papers. Once you find an interesting paper you can follow forward and backward citations to get a deeper understanding of the topic.

Conference publications are the main avenue for disseminating research results in computer science. I've highlighted a few of the top conferences in several AI areas below. Except where noted, the proceedings for these conferences should be available on-line.

First-tier Conferences:

• General AI:
  • Association for the Advancement of Artificial Intelligence (AAAI)
  • International Joint Conference on Artificial Intelligence (IJCAI)
  • Innovative Applications of Artificial Intelligence (IAAI)
• Machine Learning:
  • International Conference on Machine Learning (ICML)
  • Neural Information Processing Systems (NIPS)
• Natural Language Processing:
  • Association for Computational Linguistics (ACL)
• Computer Vision:
  • Computer Vision and Pattern Recognition (CVPR) (JMU Does not have access to full papers.)
• Robotics:
  • International Conference on Robotics and Automation (CVPR) (JMU Does not have access to full papers.)

First-tier Journals

• Artificial Intelligence Journal
• Journal of Machine Learning Research

Grading

The grade for this project will be calculated as follows:

Proposal	10%
Bibliography	20%
Poster Presentation	60%
Your Evaluations	10%

Your poster presentation will be evaluated by me, as well as by other members of the class, and possibly other members of the department. You will be evaluated both on the poster itself, and on your ability to present the contents.

Acknowledgments

This project is based on a similar project developed by George Ferguson at the University of Rochester.