Our current educational programme
Artificial Intelligence is rapidly changing the world as we know it. We see it in our day to day lives, as well as our professional environment. AI influences the way we practice our different professions and changes the way we work in and with this new tech within the academic world. Working with AI involves both knowing different techniques in the field of computer science and being able to apply these techniques in various engineering disciplines. Think for instance about how AI can influence design in general and what this means for human-computer interaction. This technology will undoubtedly play a major role in the future and as such it is important to provide society with skilled professionals.
The TU Delft educational programme in subjects related to AI, data & digitalisation is shaped by current developments and combines fundamental technology with domain-specific challenges. The subject is strongly embedded in the BSc Computer Science & Engineering, currently the biggest such educational programme in the Netherlands, and we are exploring the option of adding a BSc programme dedicated to AI Technology. At the MSc level it is embedded in the Data Science & Technology track and, as of the academic year 2020 – 2021, in the Artificial Intelligence Technology track and in the new Cognitive Robotics programme.
Collection of Master Electives on Artificial Intelligence, Data & Digitalisation
In addition to these dedicated master tracks, a university wide training programme is offered for master students from all engineering disciplines at TU Delft. Students with an interest in (the application of) AI and those who wish to incorporate such techniques in their thesis project have several options for compatible courses.
The MSc courses presented below are relevant for applying AI in any field. These are only the courses offered in the first quarter of the academic year, and are best suited for master students currently starting their second year. Students are encouraged to complete 15 EC in AI (related) courses if the elective space allows for this. The newly-developed course Applied Machine Learning (CS4305TU) will provide the backbone for any of these applied AI courses. This course is only available as elective.
Overview of electives in Q1 2020 - 2021
- Applied Machine Learning (CS4305TU)
This course aims to give students from different technical backgrounds a better understanding of a range of machine learning techniques. During the course, the focus lies on understanding how to use these different techniques, rather than on trying to improve the techniques themselves. To do this, this course will focus on demonstrating how machine learning can be used in different domains and for different types of data.
Expected prior knowledge: Python programming + Basic understanding of linear algebra & probability theory.
For more information: https://studiegids.tudelft.nl/a101_displayCourse.do?course_id=56615
For 2020 this course has a cap of 100 students due to being a pilotyear.
- Agent-based Modelling and Simulation in Air Transport (AE4422-20)
Agents and Multiagent systems. Agent-based modelling architectures. Examples from air transportation.
Emergence in Multiagent systems. Agent-based simulation. Agent-based modeling and simulation tools.
Agent-based coordination, planning, and scheduling in air transportation. Nature-inspired approaches to solve optimization problems. Swarm intelligence. Adaptive behavior and learning in agent-based systems. Collaborative decision making in air transportation. Negotiation, auctions, game-theoretic approaches. Agent-based model analysis: sensitivity, uncertainty, robustness. Validation of agent-based models.
- Remote Sensing and Big Data (CIE4616)
Many image processing and analysis techniques have been developed to aid the interpretation of a range of images (e.g. satellite remote sensing, but also other types of raster datasets like climate data) and to extract as much information as possible from the image data. Recent advances in remote sensing and computer science has moreover resulted in an explosive growth of image data sets and data analysis techniques such as machine learning. This evolution is both a challenge and opportunity as it requires specific techniques to explore, analyse, and leverage the data. This course provides an overview of tools and techniques to explore, analyse, and visualise the image data and on the implementation of big data analytics techniques on these data to exploit the growing data archives.
Expected prior knowledge: Generic programming skills.
- Computer Engineering for Scientific Computing (EPA1333)
This course offers an introduction to scientific computing: pro grammatically modelling problems and analysing data. It uses Python and a number of tools and libraries often used for scientific computing. The course provides a mix of theory and skills which are practiced using lab assignments (using Python) and discusses the following subjects:
• Programming: basic programming in Python.
• Jupyter Notebooks
• Scientific computation with libraries such as Pandas, NumPy, SciPy
• Visualization with libraries such as Matplotlib
• Other programming tools and topics (when time permits)
- Introduction to Data Science (EPA1316)
This course will train students to gather, fuse and clean data from multiple sources. In order to gain useful insights into the reality of multiple problems, we will focus on urban ecosystems. With unprecedented growth in cities, policymakers are striving to find a balance between providing equal opportunity and benefits to its citizens and sustainable development. Data science will help us understand and estimate alternative implications of solutions and communicate results to a wide audience effectively.
Expected prior knowledge: Students are not required to have prior programming experience, although it will be beneficial if you have dealt with a functional programming language like R or Python before.
- Social Signal Processing (CS4165)
The core of social intelligence is our ability to understand and interpret social signals of a person we are communicating with is. Social intelligence is a facet of human intelligence that has been argued to be indispensable and perhaps the most important for success in life. Social Signal Processing (SSP), the new, emerging, domain aimed at understanding social interactions through machine analysis and production of nonverbal behavior. In this course you will learn how next-generation computing can make use of such social signals by giving it the ability to recognize and produce human social signals and social behaviors. Think about turn taking, politeness, disagreement, emotions, rapport. You will learn about relevant findings in social psychology, and you will learn computational techniques that allow systems to make use of social signals to become more effective and more efficient by being able to detect but also simulate (e.g. in virtual agents) blinks, smiles, crossed arms, laughter. Socially aware computing. These techniques can be used in robots, virtual agents, smart homes, crowd monitoring, etc.
Expected prior knowledge: Your background should consist of a combination of at least two of these topics or related topics:
Signal Processing, Speech/Audio Processing, Computer Vision, AI, Machine Learning, Pattern Recognition, Reinforcement Learning, Deep Learning/ Neural Networks, Cognitive Modelling.
- Conversational Agents (CS4270)
Chatbots, embodied and conversational virtual agents, and social robots are becoming more and more popular. Many people are owning an Alexa, Cortana or Echo or are talking to their virtual assistant on their phone. Indeed, such technologies have the potential of making our lives easier and relieve people from the more repetitive tasks. For example, it is imaginable that such systems are being used for financial applications by helping customers with frequently asked questions but also to advise them on in the long term more impactful decisions such as their pension plans. Further applications can be imagined in the area of healthcare and education, some of which are already in existence today.
In this course, attention will be given to different verbal and nonverbal behavioral characteristics, like speech, intonation, gaze and gestures that humans show when communicating with both other people and machines. This behavior is then related to different dialogue functions, including turn-taking, addressing others, and backchanneling, that give shape to the communication process.
Expected prior knowledge: Basic programming skills (e.g. Python and Java)
Probability theory and statistics