Project Intelligent Systems

Course Objective

The course teaches students:

1. how to develop an intelligent agent (bot) based on standard Intelligent Systems technology, and extensions thereof (Knowledge and understanding) (Apply knowledge and understanding);
2. basic research and experimental analysis skills through the analysis of how effectively the developed software performs in a controlled scientific experiment. (Making judgments) (Communication)
3. how to report on their research findings. (Communication)

Course Content

In the course Project AI, a broad variety of techniques from the area of Artificial Intelligence are applied, in particular those from the course Intelligent Systems like adversarial search, knowledge representation and machine learning.

The course focuses on the development and scientific analysis of methods for rational agents that perform effectively in a game (in the past we used the Austrian trick game Schnapsen, this year we might use a different game). The outcome is a number of intelligent game-bots, and a thorough evaluation of the impact of parameters on their performance. The results of the experiments are written in a scientific report. This experience provides students with seminal skills that will be applied throughout the AI Bachelor study, and through subsequent studies and career activities. This course provides insights into how proper documentation of an experiment can ensure that:

• results are formulated objectively;
• developed scientific reports are well-specified and contain complete experiment metrics.

Additional Information Teaching Methods

There will be a few introductory lectures (refreshing relevant knowledge and introducing the practical), followed by sessions during which we discuss research methods and the academic process. The practical work will be conducted in groups, but there is also a personal evaluation component. The groups will be self-directed, and will require to consult the course assistants during practical sessions.

Method of Assessment

The course is assessed based on 3 part

1) Group

• your project idea - submitted and discussed (pass) / not submitted (fail)
• report 60% - Standard grading, no rounding

2) Individual

• Individual test 30% - Standard grading, no rounding
• Individual coding assignment 10% - Standard grading, no rounding

3) Quality of your peer review

• Pass (5.5+)/fail

To pass the course, you will need to pass each of the three parts, i.e. a grade of 5.5 or higher. You must have submitted your project idea, discussed it during your slot, and pass for the peer review. Then, your grade is computed as a weighted sum of the group and individual parts.

Not all aspects of every task will be graded (random check). For example, there are multiple peer reviews, but we might only grade some of them at random to determine your grade.

There is no resit option for this course.

Literature

Additional Information Target Audience

Additional Information

As this course is a project-oriented course, the student groups are expected to be working on this project independently for most of the time.

However, some of the meetings are mandatory to ensure a good progress of each group.

Use of generative AI is permitted in a limited way, with disclosure

In this course, generative AI (GenAI), such as ChatGPT or similar tools, may be used in a limited way, for example for editorial support, rephrasing, or structure. Substantive contributions from GenAI may only be used within the limits set by the lecturer. Any use of GenAI must always be explicitly disclosed, in accordance with the lecturer's instructions. The student remains fully responsible for the content, quality, and accuracy of the submitted work. Incorrect use of GenAI is considered fraud. If established, the submitted work or assessment result will be declared invalid, and the Examination Board may impose further measures.

Recommended background knowledge

The knowledge taught in the course Intelligent Systems and Introduction to Programming are required to succeed in the course.