URL study guide

https://studiegids.vu.nl/en/courses/2024-2025/X_401076

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 card game (the Austrian trick game Schnapsen). 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 experiment 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.

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 3-person 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 parts. First, the final group report, which contains the results of your work. There will be a combination of self and peer reviewing to individually balance grades within a group. Second, the individual test, where the students show that they can individually code an intelligent bot, create a research setup and analyze results, and report on research findings. Besides, the student will reflect on their work and show their ability to generalize their findings. This test is done in a controlled environment at the university. Third, the peer review. In this task, students provide peer reviews for other groups. The decision on whether you pass this task is made based on the quality of the reviews you write for other groups, not the reviews you receive. To pass the course, you will need to pass each of the 3 parts. For the group report and individual test, you need a grade of 5.5 or higher. For the peer review, you must get a pass (this component is graded pass/fail). Then, your final grade is computed as a weighted sum of the group report (60%) and individual test (40%). 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

The literature required for this course will be distributed via Canvas.

Target Audience

Bachelor Artificial Intelligence (year 1)

Additional Information

As this course is a project-oriented course, the student groups are expected to be working on this project individually for most of the time. However, some of the meetings are mandatory to ensure a good progress of each group.

Recommended background knowledge

The knowledge taught in the course Intelligent Systems and Introduction to Programming are required to succeed in the course.
Academic year1/09/2431/08/25
Course level6.00 EC

Language of Tuition

  • English

Study type

  • Bachelor