Course teacher(s)
Tom LENAERTS (Coordinator) and Axel ABELSECTS credits
5
Language(s) of instruction
french
Course content
This course will allow students to learn about the basics of artificial intelligence. Four themes will be covered,
- Search and planning; covering topics such as informed and uninformed search, local research, games and adversarial search.
- Probabilistic reasoning; covers topics such as Bayesian networks and Markov models.
- Decision-making under uncertainty; with topics like Markov Decision Processes and Reinforcement Learning.
- machine learning; with topics like naive Bayes, regression, perceptrons and neural networks.
Objectives (and/or specific learning outcomes)
With this course, students should have enough technical knowledge and skills to work on AI-related projects and successfully complete AI-related courses in the Master CS program at ULB and other universities.
Prerequisites and Corequisites
Required and Corequired knowledge and skills
Programming, algorithmics and standard mathematics knowledge obtained in the first Bachelor year.
Required and corequired courses
Teaching methods and learning activities
Theoretical sessions (24h) and exercises (24h) and 4 projects (60h).
- The theory session is each time 1 hour followed by a 1-hour exercises session, and this twice per week.
- The exercises are organised after each 1hour theory session, where students will solve AI problems related to each part of the course.
- The project consists of four programming assignments that will be provided during the year at different intervals. They will cover the main themes of this course.
References, bibliography, and recommended reading
This course is directly based on AI - a Modern Approach, 4th edition. There are both an English and French version of this book. You can also get access to an online copy via this link.
the ULB library also has 4-5 copies of this book available.
Course notes
- Université virtuelle
Contribution to the teaching profile
Other information
Additional information
Contacts
Tom.Lenaerts@ulb.be
Campus
Plaine
Evaluation
Method(s) of evaluation
- written examination
- Project
written examination
Project
The exam is composed of two parts.
- Theoretical exam: This exam consists of a series of problems/questions covered in the course exercise sessions. On UV, a set of exercises with solutions is provided, which contains sample exam questions.
- Practical exam: This practical exam will assess your understanding of the four projects you have completed during the year. A question will be asked on each project, and students will be assessed on their understanding and implementation skills.
The projects are coding assignments of the different parts of the course. Last year, these consisted of gridworld implementations of adversarial algorithms, probabilistic models, reinforcement learning agents, and machine learning agents. While the type of projects will be the same, the AI environment may change. These projects form the basis of the practical exam. The projects will be assessed but will not count toward the final grade.
Mark calculation method (including weighting of intermediary marks)
The course grade normally consists of two parts:
- 50% of the practical exam result
- 50% of the theory exam result
Otherwise, the score is a weighting of the results of both exams as described above.
Language(s) of evaluation
- french
- (if applicable english, Dutch )