Overview

An important part of this course is the term project. As a member of a team of around 5 students, you will apply the methods and skills learned in class (and hopefully elsewhere) to the design, prototypic implementation, and evaluation of an application. The project consists of several parts, which will be graded separately. Each team has to produce joint deliverables, which will be the basis for the grades of all team members. The team members will also be asked for feedback on the performance of the other team members. This subjective feedback may be used to adjust individual scores.

Fall 2007 Term Projects

Some pretty exciting projects were shown this term:

• Guess Who
• GTAI
• World of Warcraft
• Amoeba Arena
• Maze Runner
• Pop Song Writer
• Ant Colony
• Flux Box
• Jackpot PokerBot
• Battleship
• LEONIDAS

Project Topics

The members of a team can select their own project topic, subject to the professor's approval.

• Games: Computer games are concentrating more and more on AI techniques e.g. to generate more credible agents. Of course many of you know much more about such games than I do ;-)
• Artificial Life: The simulation of "creatures" (e.g. walkers, crawlers, worms) or populations (swarms of birds, ant hills, bee hives) frequently based on evolutionary or genetic algorithms.
• Genetic Algorithms: Conceptually a variation of search algorithms, these techniques are useful for certain optimization tasks, based on the "survival of the fittest" principle People have applied it to VLSI layout, scheduling, code generation, design optimization, and other, more exotic tasks.
• Neural Networks: These collections of simple computational elements are one of the frequently used learning methods in AI. They are used for tasks requiring classification or categorization, generalization from examples, or identification of similarities.
• Fuzzy Logic: In contrast to standard logic with its binary values, fuzzy logic employs linguistic variables such as "very tall" to capture the essential aspects. This makes many tasks such as process control much easier, but requires different reasoning methods.
• Robotics: The use of physical agents often illustrates the difference between easily solvable toy problems and their counterparts in the real world. I have one simple "Lego robot" that can be programmed in Java or a C-like language.

Schedule of Deliverables

Three deliverables are required for the project. Follow the links to descriptions of each deliverable.

Deliverable	Date Required	Marks
Project Proposal	2:00 pm, Apr 10, 2009	10
MidTerm Presentation	9:00 am May 7, 2009	35
Final Presentation	8:00 am June 4th, 2009	40
Web site	11:59 pm June 7th, 2009	15