| 03-IMAP-AML | Advanced Machine Learning (in English) You can find course dates and further information in Stud.IP. | Tanja Schultz Felix Putze |
| 03-IMAP-AMAI | Advanced Methods of AI (in English) You can find course dates and further information in Stud.IP. | Michael Beetz Dr. Daniel Beßler Oger aus Weit Weit Weg Tom Schierenbeck, ????????? |
| 03-IMS-ALLM | Advances in Lifelong Learning Machines (in English) https://lvb.informatik.uni-bremen.de/ims/03-ims-allm.pdf
Dieser Kurs findet auf Englisch statt/The course language is English.
Prior knowledge:
Basic knowledge of artificial intelligence (AI) and machine learning (ML), as acquired from
one of the introductory and foundational machine learning, AI, or cognitive systems lectures.
Advanced course knowledge, e.g. as acquired in "Life-long Machine Learning" or "Advanced
Machine Learning", is not required, but will be beneficial to engage with more recent in-depth
perspectives at the frontier of current research.
Learning Outcomes:
Traditional machine learning studies the design of models and training algorithms to learn to
solve tasks from data. In contrast to humans, who excel at adaptivity and benefit greatly from
learning curricula, machine learners are largely tailored to stationary data and static test
scenarios. Throughout the seminar, students will engage with state-of-the-art literature that
advances the frontiers of lifelong learning machines. They will improve their ability to
navigate scientific works, critically assess contributions and prospects, inspect the newest
algorithms, and identify persisting limitations and open research questions. In the process,
students will refine their scientific presentation skills and strengthen their competence in
participating in advanced machine learning discourse.
Content:
The seminar will cover different elements required to transform static machine learners into
lifelong learning machines. At the start of the seminar, students will get to select from a
choice of topics spanning a variety of modern perspectives and state-of-the-art lifelong
learning algorithms. In prospective in-depth engagement with the chosen literature as the
starting point, presentations will be prepared and held in front of the seminar participants to
fuel weekly scientific discourse. Discussed advances towards lifelong learning machines
encompass, but are not limited to:
* Memory: what consistutes memorable data points and episodes? How can we construct
concrete algorithms to identify and extract memorable experience? What types of
memories do humans possess and how do machine learning algorithms acommodate
them?
* Learning curricula: how can we identify suitable learning curricula for machine learning?
Which modern algorithms exist to enable models to benefit from structured curricula and
data streams?
* Continual optimization: how can we transcend the greediness of machine learning
optimizers? What algorithmic advances exist to effectively regularize past parameters,
representations, and knowledge?
* Adaptive and modular architectures: how can we dynamically modify opaque
architectures, such as deep neural networks? Which techniques exist to modularize
functions and disambiguate entangled representations?
* Lifelong ML theory: what are the advances in transferring machine learning theory to
lifelong machine learning? What are the insights and obstacles learned from grounded
advances analyzable, linear systems?
* Evaluation: How do we evaluate dimensions with inherent trade-offs, e.g. the pursuit of
stability and plasticity? How do we select hyperparameters in scenarios that are
constantly evolving? What techniques exist to enable fair comparisons across a
plethora of metrics of interest? | Prof. Dr. Martin Mundt |
| 03-IMAT-AU | Algorithms and Uncertainty (in English) Profil: SQ
Schwerpunkt: IMA-SQ, IMA-AI
https://lvb.informatik.uni-bremen.de/imat/03-imat-au.pdf
A key assumption of many powerful optimization methods is that all the data is fully accessible from the beginning.
However, from the point of view of many real-world applications (e.g., in logistics, production or project planning, cloud computing, etc.) this assumption is simply not true. Large data centers allocate resources to tasks without knowledge of exact execution times or energy requirements; transit times in networks are often uncertain; or, parameters such as bandwidth, demands or energy consumption are highly fluctuating. The current trend of data collection and data-driven applications often amplifies this phenomenon. As the amount of available data is increasing tremendously due to internet technology, cloud systems and sharing markets, modern algorithms are expected to be highly adaptive and learn and benefit from the dynamically changing mass of data.
In the above examples, our knowledge of the current data is only partial or based on historical estimates. The class ``Algorithms and Uncertainty'' will teach students about the most common models of such uncertain data and how to design and analyze efficient algorithms in these models.
Specifically, we will cover the theory of online optimization, where the input arrives without any prior information (such as network packets arriving to a router) and also needs to be processed immediately, before the next piece of input arrives. This model is best suited for analyzing critical networking and scheduling systems where devices and algorithms must perform well even in the worst-case scenario.
In the cases where previous history can be used to model the upcoming data, we often employ robust optimization or stochastic optimization. In robust optimization, the aim is to optimize the worst-case of all possible realizations of the input data. Hence, this model is rather conservative.
In stochastic optimization however, the algorithms work with the assumption that data is drawn from some probability distribution known ahead of time and typically the goal is to optimize the expected value.
Nowadays, another source of information is often available: machine learning algorithms can generate predictions which are accurate most of the time. However, there is no guarantee on the quality of the prediction, as the current instance may not be covered by the training set. This statement motivated a very recent research domain that will be covered in this course: how to use error-prone predictions in order to improve guaranteed algorithms.
Organization: The course will be taught in English in two sessions per week (4 SWS) including interactive exercise sessions.
Examination: The examination will be by individual oral exam. As admission to the oral exam it is mandatory to present solutions in the exercise session at least twice during the term.
Prerequisites: Having heard an introductory course to discrete algorithms and their mathematical analysis (e.g. Algorithmentheorie, Algorithmische Diskrete Mathematik) or graph theory is beneficial but not required. | Prof. Franziska Eberle |
| 03-IMAP-DGM | Deep Generative Models (in English) Schwerpunkt: IMA-AI
https://lvb.informatik.uni-bremen.de/imap/03-imap-dgm.pdf
The language of the course is English.
Learning Outcome:
In many applications of AI and machine learning the goal transcends a mere decision making process. In general, decisions should be grounded in estimates of model uncertainty, understand the underlying training distribution through learned representations, or they need to rely on data imputation. Generative models aim to address these factors, while also providing the means to further synthesize data, compress it, as well as estimate density and discover structure. Upon successful completion of the course, students will have gained an understanding of why generative models are critical, independently of whether the goal is to arrive at a decision or to generate data. They will learn the different ways to design generative models, from mixture models and probabilistic circuits, to variational, adversarial and flow-based models, all the way to large-scale models that are being referred to as Gen AI. In the process they will be equipped with the necessary
mathematical skills to understand the underlying technical foundations and engage with potential
applications.
Course Content:
* Learning and probabilistic inference
* From Gaussian mixture models to probabilistic circuits
* Latent variable models and variational inference
* Generative adversarial networks
* Flow models and change of variables
* Energy-based generative models and diffusion
* Autoregression, large language modeling, and GenAI
* Applications of generative models | Prof. Dr. Martin Mundt |
| 03-IMVP-DLS | Digital Logic Synthesis (in English) You can find course dates and further information in Stud.IP. | Prof. Dr. Rolf Drechsler Dr. Chandan Kumar Jha |
| 03-IMVA-DOMA | Domains Matter: Understanding their Influence on Natural Language Interaction (in English) Schwerpunkt: IMVA-DMI, IMVA-AI
Abstract: The shift towards human-like interaction with computers through voice and text has made large language models like ChatGPT and (…) Schwerpunkt: IMVA-DMI, IMVA-AI
Abstract: The shift towards human-like interaction with computers through voice and text has made large language models like ChatGPT and Gemini a part of everyday life. While these open-domain chatbots are powerful, their "one-size-fits-all" approach often leads to user frustrations, including the need for overly specific prompts, irrelevant or verbose responses, and a lack of critical context.
Often, domain-specific interfaces are important for improving user experience. This offers the opportunity to build specific user interfaces or manipulate the language depending on the domain. We will explore how adapting natural language interfaces to specific fields (e.g., medical advice or creative writing) can resolve these common issues. In the seminar, students will investigate a specific research question, analyze relevant academic literature, and then design, implement, and evaluate a novel domain-specific user interface. The goal is to move beyond generic chatbots and create more intelligent, context-aware, and effective natural language tools.
We will work very hands-on and will have many sessions where we implement something. For the first session bring a laptop. You should have a GitLab account and Python (version 3.10 or later) installed on your computer. The course combines research with development, and each student has to give a presentation in the course and develop a prototype. | Dr. Nina Wenig |
| 03-IMVP-ECL | Edge Computing Lab (in English) You can find course dates and further information in Stud.IP. | Thomas Dieter Barkowsky Peter Fereed Haddawy Prof. Dr. Anna Förster |
| 03-IMAA-EC1 | Entertainment Computing 1 (in English) Game Design, Games User Research und Evaluation Schwerpunkt: IMK-DMI, IMA-VMC
https://lvb.informatik.uni-bremen.de/imaa/03-imaa-ec1.pdf
Entertainment Computing I beschäftigt sich mit theoretischen Grundlagen, psychologischen Aspekten und methodischen Verfahren rund um digitale Spiele und interaktive Unterhaltungssysteme. Im Mittelpunkt stehen die Analyse und das Verständnis von Spielkonzepten, Nutzerverhalten und Evaluationsmethoden. | Prof. Dr. Rainer Malaka |
| 03-IMGS-EBDC | Experiencing Biosignal Data Collection for Cognitive Systems (in English) The kick-off meeting will take place on October 15h, 16:00 in room 2.43 of the Cartesium building. Time slots and locations of further sessions will be announced in (…) The kick-off meeting will take place on October 15h, 16:00 in room 2.43 of the Cartesium building. Time slots and locations of further sessions will be announced in the kick-off meeting.
In this course, you will take part in a large-scale data collection of biosignals, getting to hands-on experience scientific data collection, different sensors, and Virtual Reality scenarios. In the second half of the semester, you will be able to process and analyze your own data and reflect on your experience. You will learn about how dataset properties and experiment design decisions influence Machine Learning models. | Felix Putze |
| 03-IMAP-IIS | Integrated Intelligent Systems (in English) You can find course dates and further information in Stud.IP. | Michael Beetz Franklin Kenghagho Kenfack |
| 03-IMAT-IRQ | Introduction to Reversible and Quantum Computing (in English) You can find course dates and further information in Stud.IP. | Prof. Dr. Rolf Drechsler Dr. Kamalika Datta Dr. Abhoy Kole |
| 03-IMAA-ITMDS | IT-Management und Data Science (in English) You can find course dates and further information in Stud.IP. | Prof. Dr. Andreas Breiter M. Sc. Jule Jensen |
| 03-IMGS-RIG | Joint lecture series of the Robotics Institute Germany (in English) You can find course dates and further information in Stud.IP. | Nico Hochgeschwender |
| 03-IMS-APKS | Cognitive Systems Seminar (in English) You can find course dates and further information in Stud.IP. | Tanja Schultz Felix Putze |
| 03-IMVP-MLAR | Machine Learning for autonomous Robots (in English) You can find course dates and further information in Stud.IP. | Frank Kirchner M. Sc Adrian Auer |
| 03-IMAA-MAD | Mobile App Development (in English) Profil: DMI
Schwerpunkt: IMA- DMI
https://lvb.informatik.uni-bremen.de/imva/03-imva-mad.pdf
Die Veranstaltung richtet sich an Student*innen der Informatik und Digitalen Medien. In Gruppenarbeit sollen die Studierenden semesterbegleitend ein App-Projekt umsetzen. In der Vorlesung werden alle relevanten Informationen der modernen Softwareentwicklung, mit Fokus auf die mobile App-Entwickung, vermittelt. Dazu gehören Themen wie mobiles Testing, Scrum, UX Design, Evaluation & Nutzertests, Design Patterns und Cross-Plattform-Entwicklung. Das Ziel dabei ist die Vermittlung von praxisrelevantem Wissen aus dem Alltag eines erfolgreichen Unternehmens. | Prof. Dr. Rainer Malaka David Ruh Nicolas Autzen Marcus-Sebastian Schröder |
| 03-IMS-BALG | Onlien Learning: Bandit Algorithms (in English) In this seminar, we learn the basics of bandit problems and algorithms, a framework for sequential decision tasks with exploration-exploitation tradeoff. We will see (…) In this seminar, we learn the basics of bandit problems and algorithms, a framework for sequential decision tasks with exploration-exploitation tradeoff. We will see variations, extensions, and theoretical guarantees for the k-armed bandit problems and its applications in, e.g., reinforcement learning. | Prof. Franziska Eberle |
| 03-IBAP-RA | Computer Architecture and Embedded Systems (in English) You can find course dates and further information in Stud.IP. | Prof. Dr. Rolf Drechsler Dr. Muhammad Hassan |
| 03-IMAA-STMW | Search Technology for Media & Web (in English) You can find course dates and further information in Stud.IP. | Prof. Dr. Sebastian Maneth Paul Gallot |
| 03-IMS-SRSE | Seminar on Topics in Robot Software Engineering (in English) You can find course dates and further information in Stud.IP. | Nico Hochgeschwender |
| 03-IMVA-TMP | The Machinic Project (in English) You can find course dates and further information in Stud.IP. | Dr. Bernhard Robben |
| 03-IMVP-TCRS | Trustworthy Cognitive Robots and Systems (in English) You can find course dates and further information in Stud.IP. | Nico Hochgeschwender |
| 03-IMAP-VRSIM | Virtual Reality and Physically-Based Simulation (in English) Virtuelle Realität und physikalisch-basierte Simulation Profil: KIKR, DMI
Schwerpunkt: IMAP-DMI, IMAP-VMC
https://lvb.informatik.uni-bremen.de/imap/03-imap-vrsim.pdf
English or German.
Over the past two decades, VR has established itself as an important tool in several industries, such as manufacturing (e.g., automotive, airspace, ship building), architecture, and pharmaceutical industries. During the past few years, we have been witnessing the second "wave" of VR, this time in the consumer, in particular, in the entertainment markets.
Some of the topics to be covered (tentatively):
• Introduction, basic notions of VR, several example applications
• VR technologies: displays, tracking, input devices, scene graphs, game engines
• The human visual system and Stereo rendering
• Techniques for real-time rendering
• Fundamental immersive interaction techniques: fundamentals and principles, 3D navigation, user models, 3D selection, redirected walking, system control
• Complex immersive interaction techniques: world-in-miniature, action-at-a-distance, magic lens, etc.
• Particle systems
• Spring-mass systems
• Haptics and force feedback
• Collision detection
• Acoustic rendering
The assignments will be mostly practical ones, based on the cross-platform game engine Unreal. Participants will start developing with "visual programming", and later use C++ to solve the assignments.
You are encouraged to work on assignments in small teams.
https://cgvr.cs.uni-bremen.de/teaching/ | Prof. Dr. Gabriel Zachmann |
