Research course

This course provides you with a solid understanding of empirical research methods. You learn to set up a research study, collect and analyse data, and draw scientifically valid conclusions. Emphasis is placed on reproducible research practices, including techniques like pre-registration, and creating a data plan. To make sense of data samples, you study how to make statistical inferences about the population. You explore frequentist and Bayesian data analysis approaches, gaining the ability to make meaningful statistical inferences based on collected data. The course covers working with different types of datasets, including high-dimensional data sets such as images and longitudinal data.

In this course, you will read scientific journal and conference articles from the field of programming languages, and learn about state of the art tools and principles for language engineering. You will also do a course capstone project related to a research problem, applying methods, knowledge, and techniques from the programming language literature. Possible projects could for example be implementing a small programming language using a language workbench, creating an embedded domain-specific language with a unique feature, extending an existing compiler with a new code transformation or optimization, or using a proof assistant to formalize and prove things about a language or code transformation.

The security of computer and telecommunication systems is becoming an increasing concern. In this course, we will review the current state of the art on security research, gain practical experience in assessing the security and vulnerabilities of communication systems, and discuss security principles, common pitfalls, and vulnerabilities. You will engage in hands-on "Hack Projects" where you evaluate real-world IT systems, develop proof-of-concept exploits, or address privacy concerns. These projects, documented in scientific-style reports, cover a wide range of hardware and software topics, with findings presented to the class and code made publicly available for reproducibility and further research.

Intelligent decision making is a key skill of computational agents. Research on this topic focuses on building models and algorithms that enable AI systems to take appropriate decisions. Building upon theoretical knowledge gained in the Algorithmics theme, you collaborate in small groups on a distinct research project per group, for instance on decision-making problems in transport, logistics or smart energy grids. Purely algorithmic challenges will also be provided. The research projects provide a good opportunity to learn about topics suitable for your Master thesis project.

This course provides a comprehensive introduction to the field of program analysis, a critical aspect of software development and maintenance. Students will delve into both theoretical foundations and practical applications, learning how to analyse, understand, and improve software systems. The course covers a wide range of techniques, including static analyses, data flow and control flow analyses, and various approaches to model and analyse source code. Through hands-on project, you will gain experience, understanding and will apply these techniques and present them using a scientifically valid methodology.

Social Signal Processing and Affective Computing, aims to develop automated approaches that can interpret human social and/or affective behaviour through machine analysis and production of nonverbal and verbal behaviour.

In this course you will learn how next-generation computing can make use of such social and affective signals by giving it the ability to recognize and produce human social signals and social behaviours. You will learn about relevant findings in social psychology, and computational techniques that allow systems to make use of social and affective 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. These techniques can be used in robots, virtual agents, smart homes, crowd monitoring, among others.

This course delves into recent advancements in web data and information management, covering topics such as web technology, web data management, web data semantics, web data analytics, the social web, and web science. You will explore these subjects alongside learning about the role of scientific communication and about the scientific methodologies and approaches for conducting research in this field.

In this research course you conduct deep investigation of recent techniques solving attractive problems in a research area of Computer Graphics including Visualization, Interaction, Image Processing, Inverse rendering, and 3D data processing. You will survey research outputs in the area of your interest, present a selected paper and develop an implementation supporting the education on the topic. The goal is to strengthen your analytical and presentation skills and prepare you for research in your Master thesis project.

Through all the exciting recent advances in digital media technology and the rapid growth of social media platforms, multimedia content is increasingly embedded in our daily lives, gaining enormous potential in improving the traditional educational, professional, business, communication and entertainment processes. To be able to use this potential for transferring these processes into user-centric interactive multimedia applications, technology is required that can help us access, deliver, enrich and share rich-media content. This course provides insight into the state-of-the-art cross-disciplinary research efforts related to the development of such technology. The topics covered by the course include, but are not limited to, multimedia systems, multimedia experiences, and multimedia engagement.

This seminar course focuses on the design and construction of parallel and distributed machine learning (ML) and deep learning (DL) solutions. Through activities like paper reading, presentations, discussions, and project prototyping, you will gain insight into state-of-the-art algorithms and systems, emphasizing scalability, resource efficiency, data requirements, and robustness. Topics covered include parallel and distributed ML/DL algorithms, performance and scalability of systems, hardware-accelerated solutions, federated machine learning systems, and deep generative learning systems, with special attention to mapping solutions to AI accelerators and managing large-scale distributed workloads effectively.