Specialisation Artificial Intelligence

About

The AI specialisation is all about building intelligent software artefacts. We emphasise the theories of complex dynamic systems and self-organisation, starting from the theory of complex dynamic systems as developed in related fields, such as mathematics, physics and biology. In addition to data mining and big data, students will be exposed to current research in the areas of adaptive systems, multi-agent systems, the origins of language and bioinformatics.

In Detail

The VUB’s AI Laboratory is the longest-established AI research centre in mainland Europe, dating from 1982. Our unique history and expertise gives our Artificial Intelligence (AI) master’s specialisation broad and deep expertise in Artificial Intelligence research and technology, covering foundations of the field right through to the latest developments. The specialisation is focused on AI engineering skills: you will learn to program computational intelligent systems and to study their capabilities rigorously. Having successfully finished the specialisation, you will be well-prepared for a career in Artificial Intelligence, at the cutting edge of the current wave of intelligent computational systems. Acknowledging that AI changes very quickly, this specialisation aims to equip you with the technical and intellectual skills of an independent self-directed learner, who is able to stay ahead of the current trend and thus contribute to industry or academia at the highest possible level throughout an exciting career.  

As a student in the AI specialisation, you will study, use and apply state-of-the-art AI techniques, including logic-based, statistical and probabilistic, and neural inference systems, cognitive modelling, multi-agent societies with emergent intelligence, language processing, reinforcement learning and computational creativity, all set in a rigorous mathematical and scientific context, bridging the gap between application and theory. In your Master’s thesis, you will conduct original research under the guidance of an internationally renowned AI specialist, and your work may well contribute to the ongoing projects of the Lab, making a lasting contribution to AI science.

The AI specialisation comprises three mandatory courses and a broad choice of electives that allow you to put your own personal emphasis on your studies. For example, you can learn how to store knowledge so that it can be understood both by humans and computers, and how to use it afterwards to automatically solve problems; if you are interested in machine learning, you can study how computers and robots can learn by searching for interesting patterns in data, or how they can learn from experience and get gradually better at performing a task; if you are interested in language you can study how artificial intelligence can be used to investigate how language works, how it evolved, and how computers can understand, produce and learn it; if you are interested in how computers might contribute to creative activities in science, arts and music, you can study creative production from the cognitive perspective (how do humans do it?), from an engineering perspective (which AI systems can do it?) or from a philosophical perspective (what is creativity anyway?); if you are interested in the effect of AI on the world, you can study its ethics and social impact. The choice is yours.

Artificial Intelligence is a specialisation in our 2-year MsC in Computer Science of 120 ECTS. Students of this specialisation need to succeed for the carefully designed core of 30 ECTS that is common to all four specialisations, the 18 ECTS of three mandatory courses within this specialisation, at least 12 ECTS of electives within the specialisation, an additional 30 ECTS of electives from this or any of the other specialisations, and for a research training of 6 ECTS and a master's thesis of 24 ECTS.

The following is the list of mandatory courses:

Statistical Foundations of Machine Learning (foundational, 6 ECTS, sem 2)
Machine Learning is applicable to many real-world tasks, and mainly consists of learning correlations in data, or between inputs and outputs. This course explains all the fundamental aspects of the most common Machine Learning approaches, to allow the students to perfectly understand how to design well-behaving Machine Learning systems, accurately measure their performance, and use the result of the learning procedure as efficiently as possible. This course also explains how various algorithms work, such as least-squares regression, neural networks or decision trees.
Actual Trends in Artificial Intelligence (deepening, 6 ECTS, sem 1+2)
Artificial Intelligence is moving at an incredible pace. In this course, the latest progress in state-of-the-art AI is introduced. Over the course of ten guest lectures, experts in their field come to talk about their latest research. Next to the theoretical part, in the AI challenges students will apply learned techniques in a team, to create an AI powered application!
Computational Game Theory (foundational, 6 ECTS, sem 1)
Just as humans, AI systems don’t live in isolation. It doesn’t make sense to make a single traffic light smart, rather the traffic lights need to organise themselves as a team to optimise traffic throughput. The aim of the course is to introduce the students to the field of learning agents, where the learning happens in a group or population of agents. The students will also obtain a basic understanding of (evolutionary) game theory and complex networks which will allow them to understand the scientific literature in that field and the relevance of this domain to learning in general.

Artificial Intelligence is a specialisation in our 2-year MsC in Computer Science of 120 ECTS. Students of this specialisation need to succeed for the carefully designed core of 30 ECTS that is common to all four specialisations, the 18 ECTS of three mandatory courses within this specialisation, at least 12 ECTS of electives within the specialisation, an additional 30 ECTS of electives from this or any of the other specialisations, and for a research training of 6 ECTS and a master's thesis of 24 ECTS.

The following is the list of electives within this specialisation:

Adaptive Systems Seminar (deepening, 6 ECTS, sem 2)
During this course we will watch and discuss a number of video lectures from MLSS, which is a recurring summer school for PhD students in machine learning. The lectures are given by top experts on the corresponding topic.
Processus dynamiques (broadening, 5 ECTS, sem 2)
This course provides an introduction to important techniques for analysing stochastic and dynamic processes such as waiting queues and inventory control systems.
Reinforcement Learning (deepening, 6 ECTS, sem 1+2)
Through lectures and a project (no exam), we explore how to design learning agents with Reinforcement Learning. Reinforcement Learning is a learning paradigm where agents observe their state and execute actions and received feedback. Based on this feedback, they gradually learn to maximize the reward they obtain and become better and better in the task they need to perform. Pretty much like how children learn to ride a bike. The seminar explains various ways of designing practical agents, from very simple to complex (deep) and the multiple settings in which Reinforcement Learning is applicable..
Evolution of speech (broadening, 6 ECTS, sem 1)
In this course we study a series of computational techniques that are used to model speech and language. We apply these to the case of studying speech and language from an evolutionary perspective. The two aims of the course are to introduce computational models of speech and language and to show how AI-techniques can be used to study a broader scientific question.
Discrete Modeling, Optimization, and Search (deepening, 6 ECTS, sem 1)
In this module we study modern techniques for combinatorial search and the knowledge representation formalism "answer set programming". In the latter, combinatorial search or optimization problems are described in a high level language and as such, formulation of the problem and method by which to find solutions are completely separated.
Computational Creativity (broadening, 6 ECTS, sem 2)
Computational Creativity is the study of computational systems that are capable of doing things that, if a human did them, would be called creative. This includes art, music and literature, but also recipe design, science, engineering and mathematics. This course covers the philosophy, science and technology of computational creativity in a mixed series of lectures and seminars. Each student builds their own computationally creative system.
Computer Vision (broadening, 4 ECTS, sem 1)
This course aims for students to understand and apply fundamental mathematical and computational techniques in computer vision, and for students to implement basic computer vision applications.
Swarm Intelligence (broadening, 5 ECTS, sem 2)
Swarm intelligence is the discipline that deals with natural and artificial systems composed of many individuals that coordinate using decentralized control and self-organization. In particular, the discipline focuses on the collective behaviors that result from the local interactions of the individuals with each other and with their environment. Examples of systems studied by swarm intelligence are colonies of ants and termites, schools of fish, flocks of birds, herds of land animals.
Advanced Methods in Bioinformatics (deepening, 6 ECTS, sem 2)
This course focuses on algorithms and methods in computational biology, with active participation of the students in implementing such algorithms. The course covers methods and associated algorithms for solving problems related to protein sequences, protein evolution and protein structure, as well as Next Generation Sequencing data analysis and strategies for the discovery of regulatory motifs, in particular genomics and transcriptomics data in relation to cancer.
Artificial Intelligence Programming Paradigms (broadening, 6 ECTS, sem 2)
This course covers some of the most central topics in symbolic AI programming, including unification, problem solving through search, heuristics, meta-layer architectures and computational reflection. In this course, you will gain both a theoretical and practical understanding of fundamental concepts in AI programming, which will enable you to build your own intelligent systems.
Natural Language Processing (deepening, 6 ECTS, sem 1)
In this course you will build intelligent systems that are able to interact with their environment through natural language. The fundamental idea behind this is that the meaning of natural language expressions can be modelled as executable programs. The student will acquire the necessary knowledge and skills to manage a challenging AI research project in the subfield of situated natural language understanding.
Decision Engineering (broadening, 5 ECTS, sem 2)
The goal of this course is to introduce the basics of decision theory. The main aim is to illustrate how mathematical models and specific algorithms can be used to help decision makers facing complex problems (involving a large number of alternatives / multiple criteria / uncertain or risky outcomes / multiple decision makers, …).

Artificial Intelligence is a specialisation in our 2-year MsC in Computer Science of 120 ECTS. Students of this specialisation need to succeed for the carefully designed core of 30 ECTS that is common to all four specialisations, the 18 ECTS of three mandatory courses within this specialisation, at least 12 ECTS of electives within the specialisation, an additional 30 ECTS of electives from this or any of the other specialisations, and for a research training of 6 ECTS and a master's thesis of 24 ECTS.

Click here to consult the official program overview for the complete list of electives.

In addition, up to 12 ECTS can be chosen from our Bachelor programme in Computer Science with approval of the examiniation commission.