Techniques of Artificial Intelligence

This course provides an introduction to both classical and modern approaches in Artificial Intelligence (AI). While recent breakthroughs in Machine Learning and Deep Learning have brought AI into the spotlight, the field encompasses a much broader range of techniques and ideas. The course covers the following topics:

• Agent and Search
• Constraint Satisfaction Problems
• Adversarial Search and Uncertainty
• Markov Decision Processes
• Reinforcement Learning
• Bayesian Networks
• Naive Bayes and Decision Trees
• Neural Networks
• Large Language Models
• Responsible AI

The primary goal of the course is to give students a comprehensive overview of AI, covering foundational concepts as well as current trends. In addition to theoretical understanding, students will gain hands-on experience through practical exercises and a software project. 

Cours ayant celui-ci comme co-requis

The course consists of a series of lectures and practice sessions.

References, bibliography, and recommended reading

The course is based on the following two textbooks:

• Artificial Intelligence: A Modern Approach, 4th Edition, 2021. Peter Norvig and Stuart J. Russell. Pearson Education.
• L'intelligence artificielle en pratique avec Python : recherche, optimisation, apprentissage, 3rd Edition, 2024. Hugues Bersini and Ken Hasselmann. Eyrolles.

Course notes

• Université virtuelle

Contacts

Dimitris Sacharidis <dimitris.sacharidis@ulb.be>

Campus

Solbosch

Method(s) of evaluation

• written examination
• Project

written examination

• Open book examination

Project

The evaluation is based on a programming project and a written exam.

Mark calculation method (including weighting of intermediary marks)

• 50% from the programming project
• 50% from the written exam

Language(s) of evaluation

• english