6 ECTS credits
160 h study time
Offer 1 with catalog number 4004728DNR for all students in the 2nd semester at a (D) Master - preliminary level.
This course introduces the field of Artificial Intelligence and highlights several key techniques. A first part of the course focuses on the history and principles of AI, and how intelligent agents interact with various kinds of environments.
The basic principles of machine learning form the second part of the course, which introduces supervised and unsupervised learning, and classification and regression problems.
To obtain insight into the workings of such methods, several key techniques such as decision trees, artificial neural networks, and Bayesian probabilistic classifiers are discussed in detail.
A third part deals with classical or rule-based AI, including problem-solving methods and search such as A* search, and gameplay strategies such as minimax and alpha-beta pruning. The basics of knowledge representation and reasoning are also discussed.
The last part of the course deals with the ethical considerations of AI, exploring aspects such as fairness, bias, and dual use.
For more information about the specifics of this course, please consult the online learning platform Canvas.
Knowledge and insight
The student is acquainted with commonly used AI techniques, including learning algorithms.
The student can recognize, explain, and illustrate key concepts of AI such as intelligent agents, performance metrics and environments.
The student can describe how knowledge is represented and how reasoning can take place in an automated way.
The student can explain and illustrate some commonly used AI techniques, including search strategies and machine learning algorithms.
The student can correctly trace a machine learning algorithm, such as building a decision tree from a small data set.
The student can autonomously design a machine learning experiment, including a correct use of the data for training, validation and testing.
The student can autonomously choose the appropriate techniques given a concrete learning problem.
The student can correctly apply a machine learning technique on a complex learning problem.
The student can analyse and interpret the outcome of a given algorithm when applied to problems with varying degrees of complexity.
The student can apply evaluation methods to estimate the performance of a machine learning algorithm given a concrete application.
Judgement ability
The student can devise and sustain arguments in favor of, or against some choice of (learning) technique for a given problem.
The student can identify potential biases and limitations of a machine learning application.
Communication
The student can motivate the chosen approach to specialist and non-specialists.
Skills
The student has obtained the skills to autonomously program, analyse, and apply AI techniques to a wide variety of problems.
The student can write well-documented code to prepare a dataset, apply a machine learning technique and evaluate the results.
This course contributes to the following programme outcomes of the Master in Applied Computer Sciences:
MA_A: Knowledge oriented competence
1. The Master in Engineering Sciences has in-depth knowledge and understanding of exact sciences with the specificity of their application to engineering
3. The Master in Engineering Sciences has in-depth knowledge and understanding of the advanced methods and theories to schematize and model complex problems or processes
4. The Master in Engineering Sciences can reformulate complex engineering problems in order to solve them (simplifying assumptions, reducing complexity)
5. The Master in Engineering Sciences can conceive, plan and execute a research project, based on an analysis of its objectives, existing knowledge and the relevant literature, with attention to innovation and valorization in industry and society
6. The Master in Engineering Sciences can correctly report on research or design results in the form of a technical report or in the form of a scientific paper
7. The Master in Engineering Sciences can present and defend results in a scientifically sound way, using contemporary communication tools, for a national as well as for an international professional or lay audience
11. The Master in Engineering Sciences can think critically about and evaluate projects, systems and processes, particularly when based on incomplete, contradictory and/or redundant information
MA_B: Attitude
13. The Master in Engineering Sciences has a critical attitude towards one’s own results and those of others
27. The Master in Applied Computer Science is aware of and critical about the impact of ICT on society.
The final grade is composed based on the following categories:
Written Exam determines 50% of the final mark.
Other Exam determines 50% of the final mark.
Within the Written Exam category, the following assignments need to be completed:
Within the Other Exam category, the following assignments need to be completed:
The exam consists of a closed book written exam and a project related to machine learning.
The goal of the project is to design ML solutions for a given problem and data set in a scientifically correct way. Project deliverables include well-documented source code implementing the machine learning project and a scientific presentation. The realization of the learning outcomes and the student's understanding and authorship of the project are assessed in a thorough individual oral Q&A session.
Intermediate deadlines may be imposed to ensure continuous evaluation.
Weighting:
50% closed book exam.
50% project work.
Partial results: If the total mark is unsatisfactory, a passing mark on either of the parts will be retained to the second examination period.
A late submission of the project report will result in a mark of 0 for the project work.
This offer is part of the following study plans:
Master of Biomedical Engineering: Standaard traject (only offered in Dutch)
Master in Applied Sciences and Engineering: Applied Computer Science: Standaard traject
Master of Biomedical Engineering: Startplan
Master of Biomedical Engineering: Profile Radiation Physics
Master of Biomedical Engineering: Profile Biomechanics and Biomaterials
Master of Biomedical Engineering: Profile Sensors and Medical Devices
Master of Biomedical Engineering: Profile Neuro-Engineering
Master of Biomedical Engineering: Standaard traject (NIEUW)
Master of Biomedical Engineering: Profile Artificial intelligence and Digital Health