Artificial Intelligence
Micro-credential
February – June 2026
This course aims at providing insight in the fundamental concepts of the theory and applications in the broad Artificial Intelligence discipline. An overview of the most commonly used methods and models is presented, of which a number are treated in depth. Especially, focus is put on the topic Machine Learning (particularly neural networks and deep learning) and data driven model building, including Bayesian learning. We start from the theory of supervised learning with basic linear regression and linear classification problems gradually building towards more complex supervised learning tasks. Then we turn to unsupervised learning, and particularly dimensionality reduction and clustering. The course also places machine learning into a broader perspective of Artificial Intelligence, where we also investigate problem solving agents (search and game playing), decision problems (including Markov decision processes), and basics of reinforcement learning.
In this way, by the end of the course, all the concepts and topics covered are brought together to tackle the most challenging problems of autonomous decision-making and rational action under uncertainty.
The theoretical classes are complemented by exercises, including computer-based exercises and demonstration sessions
This course is targeted at professionals who are involved in, or impacted by, the development and deployment of intelligent systems and wish to deepen their understanding of Artificial Intelligence. It is designed for those seeking to advance their skills in designing, evaluating, and implementing AI techniques for automatic data analysis, such as classification and clustering, as well as for more complex tasks involving decision support and automation.
Most participants will have a background in engineering or computer science, but the course is open to people with a different background who have experience with the following:
- Have basic programming skills in Python
- Have knowledge of and the ability to apply basic machine learning algorithms
Micro-credentials are small courses of academic level that focus on specific competencies. They often consist of one or several subjects which are also taught in an university bachelor's or master's degree.
If you pass the micro-credential, you will receive a certificate as proof that you have completed the acquired competencies. So you also acquire real official credits who are recognized in your further career, also internationally. They can also lead to exemptions for other courses, also at other institutions and organizations.
You will receive a certificate of the micro-credential + credit certificate when you pass the corresponding exam (6 ECTS points).
Examination method
- Written exam (closed book, closed personal notes except summary on 1 page, A4 format)
- Evaluation of practical work in groups, spread over the semester, as well as individual home work assignments.
Prof. Aleksandra Pizurica, of Telecommunications and Information Processing, Ghent University
Content
Module 1: Introduction: survey of AI
- Survey of AI
- Fundamental machine learning concepts (dataset, training set, validation set, dimensionality, overfitting, bias and variance, cross validation)
- The rational agent concept
- Introduction to search problems and games
Module 2: ML: Regression and Classification
- Logistic regression
- Classification
- Clustering
- Construction of data driven models
- white-box models and parameter estimation
- black-box models (Perceptron and neural networks)
Module 3: ML: Reasoning under uncertainty
- Bayesian reasoning and learning
- Bayesian networks and inference
- Design Of Experiment
Module 4: Societal context
- Ethical dimension
- Limitations of AI/ML
- Illustrations
Module 5: Search problems
- Informed search; local search
- Games (minimax, expectimax)
Module 6: Decisions and actions
- Rationality, Decision networks
- Markovian Decision Problems (MDP)
- Reinforcement Learning (RL)
Module 7: More advanced AI
- Reasoning over time; Prediction; Viterbi
- Fundamentals on Hidden Markov Models and Dynamic Decision networks
- Examples from Robotics and/or Computer vision and/or NLP
Final competences
- Having an overall view on the different generic problem classes in the AI discipline
- Having insight in the fundamentals and concepts underlying commonly used solution techniques in this discipline, especially focussing on data driven model construction (white box as well as black box)
- Having a thorough understanding of search strategies, focussing on decision problems (Markovian Decision Problems and the connection to Reinforcement Learning, planning problems in dynamical environments).
- Solving specific problems in AI using the methods of this course (and extending these methods as needed in terms of applicability and context), as well on paper as in Python.
- Being able to assess the limitations and ethical consequences of AI-techniques.
Practical info
Fee
384,80 euro
Click here for more information about the billing process and the payment request.
A payment request is always addressed to the student.
If your company or employer wants to pay your tuition fee they can do so by using the reference mentioned on the payment request.You can also make the payment yourself and ask for a proof of payment by sending an email to studiegeld@ugent.be.
This proof of payment can then be used as an expense report.
FYI: there is no VAT on the tuition fee. Therefore it is unnecessary to mention the name and VAT number of the company on the payment request.
SME e-wallet
Ghent University accepts payments via the SME e-wallet.Go to www.vlaio.be/en/subsidies/sme-e-wallet and use authorization code DV.O103193.
Opleidingsverlof (VOV)
This training is recognized in the context of VOV. For each credit point you are entitled to 4 hours of VOV.This course (6 ECTS points) covers in total 24 hours of VOV (participation at the assigments and the exam is mandatory).
The registration certificate for VOV can be found at your personal page in OASIS (student administration platform).
You can download this yourself. For administrative reasons, it's helpful to write the registration number ODB-P00004 on the certificate yourself. (Oasis > My Oasis > certificates > select correct academic year > document ‘enrolment certificate for APOP’).
Certification of exam participation is done automatically.
Enroll here: studiekiezer.ugent.be/2025/micro-credential-artificial-intelligence-en
A manual to enroll can be found here.Please select ‘microcredential’ when you subscribe!
The course starts on Tuesday 10 February 2026 and will always take place on Tuesdays from 16h till 18h45 at Campus Ledeganck, K.L. Ledeganckstraat 35, auditorium 4 and on Thursdays from 14h30 till 17h15 at Campus Ardoyen, Technologiepark Zwijnaarde, building 126 (IGent), auditorium 1.
Download a map of Campus Ledeganck & Campus Ardoyen here..
The last lesson will be given on 12 May 2026.
Note: paid parking.
- The training is supported by the Ufora learning platform, which contains, among other things, the course material.
- A personal laptop is required (which must be able to run x86 virtual machines).
- Participants take the classes together with students of the Bachelor of Science in Computer Science Engineering and of the Bridging Programme Master of Science in Computer Science Engineering.
Organisation
Universiteit Gent
UGent Academie voor Ingenieurs
Technologiepark 60
9052 Zwijnaarde
Tel.: +32 9 264 55 82
ugain@UGent.be