CS540 Spring 2009 Project

Projects afford students the chance to explore some topic of specific interest to them. In this class, projects may consist of an application using a publicly available AI system or tool, critical analysis of research in a new hot topic, implementations of artificial intelligence techniques other than those developed in class, application of discussed techniques to real problems, replication of a prior study, or some combination of the above. The project must include some implementation or evaluation component.

Because other graduate AI courses are taught in computer vision, statistical machine learning and bioinformatics, your project must focus on an AI topic outside of those areas. You may include some aspect of the topics covered in other classes as a minor part for comparison or to provide some needed functionality, but other areas must not be the focus.

If you are in doubt,...
come talk to the instructor.
If you are also taking CS580 or CS510 and want to pursue a larger project that satisfies requirements in both courses,...
come talk to the instructors.
If you want to work in a team,...
come talk to the instructor.

Project proposals must be submitted by February 12 (beginning of class). Proposals should be 1-2 pages, and should briefly describe what problem is being solved or question(s) answered, if it is a team or joint CS545 or CS510 project, why it is appropriate for this course. Include any citations or background information sketching what has been done before. Note: I must see at least two citations to demonstrate that you've at least checked what has been done before. Citation should be of a paper that was published in a peer reviewed venue (conference, workshop or journal); some random person's web site, blog or unrefereed student paper does not count.

At some time during the semester, you will do a progress report; size permitting, we will do them in class. During the last week of the semester, each project will be presented to the class. A written report describing what was done is also required.

Experiment Design

On April 16 by the start of class, you need to hand in an experiment design. It should include the following parts:

Hypothesis or Hypotheses: What are you testing with your experiment? What is the hypothesis(es) underlying the experiment? Briefly why is this your hypothesis.
Independent Variables: List the variables to be observed or, more likely, controlled. List also the values that you will be controlling for each of the variables. Indicate how these variables relate to the hypothesis.
Dependent Variables: List the variables to be measured and describe their relationship to one another and the hypothesis.
Exogenous Variables List the variables that you think might influence the outcome, but that are not to be manipulated. If they are being set to a particular value (e.g., you are using a specific computational platform), state what that is and why.
Experiment Protocol Describe the procedure for running your experiments. If you will be running multiple trials of some factor combinations, state how many.
Visualizations How will you examine the data? How will you display it in your paper?
Statistical Analyses What statistical tests will you run? How do they relate to your hypothesis? If they are parameteric, how will you check that they are appropriate? What value of alpha will you use?
Expected Conclusions Pretend to write the conclusion paragraph describing what you found (be optimistic!) and how the experiment supported your conclusions.

Project Final Reports

During the last week of classes, each student will present a verbal report on their project. We will have 2 sessions; consequently, each student gets 15 minutes for their talk plus 4 minutes for changeover and questions. Look at the guidelines for the written report to get an idea of some of what should be covered. Since we have heard your progress report, remind us briefly of your project (what you talked about before), but emphasize what you have done since and what you will expect to conclude in your final report. The instructor will give you feedback, based on this presentation, to help you better prepare your final report.

You will be required to hand in a written project report during finals week. The guielines for this report are here.

Project titles

Spring 2005:

Uninformed World Exploring Agents
Alternative Data Mining Techniques for Predicting Tropical Storm Intensification
Examining Move Operators for Dynamic Basis Function
Using Genetic Algorithms to Weight an Evaluation Function for Tetris
Evolving Cellular Automata to Perform Computation
Learning trust in multi-agent systems using belief (Bayesian) networks

Spring 2006:

Particle Swarm Intelligence and Multi-funnel functions
Comparison of GA strategies on traclabs' BIOSIM
Two Heuristics for Resource Allocation in a Heterogeneous computing System
Empirical Studies in Genetic Algorithms and Genetic Programming using the Game of Othello
Using AI To Guide Performance Transformations For Irregular Applications
Cracking Transposition Ciphers
Habitat longevity optimization using genetic algorithms
Application of Genetic Algorithms to the Dynamic Job Shop Problem
A Fuzzy Clustering approach to filter Spam E-Mail

Spring 2008:

Literature Based Discovery
Automatic Tower Defense
Bounding Local Minima and Plateaus in Image Congealing
Elevator Dispatching Problem
A Different Approach for SLS-THC: Stochastic Local Search Algorithm with Violations-Directed Random Walk