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.

Die Veranstaltung findet zusammen mit der FTH-13 statt.
The course will offer a panorama view of Discrete Mathematics, which is a core subject of mathematics with impact on algebra, topology and geometry.
Discrete structures are the main building blocks in algorithm design, and the class will also cover some algorithmic aspects, making it of interest to CS majors. Furthermore, counting techniques and asymptotic estimates are of use in discrete probability, so the class is also suitable for math majors interested in statistics.

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.

Die Veranstaltung findet zusammen mit 03-M-FTH-10 statt.

The course is dedicated to the numerical solution of partial differential equations. The focus is on finite differences and finite element methods.

Partial differential equations are a main component in the modelling of physical, chemical or biological phenomena in several spatial dimensions or in space and time. They also often occur in mathematical problems in geometry or calculus of variations. The lecture deals with the discretisation of partial differential equations and the estimation of the error between continuous and discrete solution. In particular, the finite difference and the finite element method are introduced and investigated. We first discuss the application of the methods to stationary elliptic problems. Later also time-dependent problems are considered. The connection of theory, numerical analysis and implementation is particularly important.

Finding a route that minimizes the travel time from Bremen to another city is easy if all information is available upfront. In reality, when starting the trip we have to decide on a mode of transport and the first parts of our route while information about congestion, and road or train track blockages become available over time. In online optimization, we address such problems where input information is revealed step by step while some parts of the solution are already fixed.

The quantitative assessment and the management of (extreme) risks are key tools for policy makers and stakeholders in many areas such as climate and environmental research, economics, or finance and insurance. In this course, we will get familiar with basic mathematical concepts of (quantitative) risk assessment and management.

Lecture under the specialization
1) Statistics/Stochastics
2) Data Analysis

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.

Die Veranstaltung findet zusammen mit der FTH-13 statt.
The course will offer a panorama view of Discrete Mathematics, which is a core subject of mathematics with impact on algebra, topology and geometry.
Discrete structures are the main building blocks in algorithm design, and the class will also cover some algorithmic aspects, making it of interest to CS majors. Furthermore, counting techniques and asymptotic estimates are of use in discrete probability, so the class is also suitable for math majors interested in statistics.

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.

Die Veranstaltung findet zusammen mit 03-M-FTH-10 statt.

The course is dedicated to the numerical solution of partial differential equations. The focus is on finite differences and finite element methods.

Partial differential equations are a main component in the modelling of physical, chemical or biological phenomena in several spatial dimensions or in space and time. They also often occur in mathematical problems in geometry or calculus of variations. The lecture deals with the discretisation of partial differential equations and the estimation of the error between continuous and discrete solution. In particular, the finite difference and the finite element method are introduced and investigated. We first discuss the application of the methods to stationary elliptic problems. Later also time-dependent problems are considered. The connection of theory, numerical analysis and implementation is particularly important.

Finding a route that minimizes the travel time from Bremen to another city is easy if all information is available upfront. In reality, when starting the trip we have to decide on a mode of transport and the first parts of our route while information about congestion, and road or train track blockages become available over time. In online optimization, we address such problems where input information is revealed step by step while some parts of the solution are already fixed.

The quantitative assessment and the management of (extreme) risks are key tools for policy makers and stakeholders in many areas such as climate and environmental research, economics, or finance and insurance. In this course, we will get familiar with basic mathematical concepts of (quantitative) risk assessment and management.

Lecture under the specialization
1) Statistics/Stochastics
2) Data Analysis

Die Veranstaltung findet zusammen mit der MKOM-13 statt.
Seminar on selected topics of algebraic topology

Die Veranstaltung findet zusammen mit der MKOM-13 statt.
Seminar on selected topics of algebraic topology

Many every-day processes can seen as a game between autonomous interacting players, where each player acts strategically in order to pursue her own objectives. This seminar covers various game-theoretic concepts and techniques, mainly with connections to applications. Use-cases are distributed systems, auctions, online-markets, resource allocation, and traffic networks.

The seminar is based on the so-called "29th Internet Seminar 2025/26", see
https://www.fan.uni-wuppertal.de/de/lehre/29th-internet-seminar/
The main topics are eventually positive resolvents and semigroups, first in finite dimensional spaces and then in Banach spaces - or to be more precise in Banach lattices, which is a convenient setting for the study of (eventual) positivity.

Seminararbeit und Vortrag über ausgewählte Publikation aus dem Bereich der Visualisierung großer wissenschaftlicher Datensätze

In this course Robust control is introduced. Robust control is an approach to design controllers to deal with uncertainty. The aim is to achieve robust performance (or stability) in the presence of bounded modelling errors.

Many phenomena in nature, in technology, and in economics possess spatial, temporal, or spatio-temporal dynamics. In a probabilistic or statistical modeling framework, such dynamics are expressed by means of dependency models, dependency structures, or dependency measures. These are the topics of the seminar.

Many every-day processes can seen as a game between autonomous interacting players, where each player acts strategically in order to pursue her own objectives. This seminar covers various game-theoretic concepts and techniques, mainly with connections to applications. Use-cases are distributed systems, auctions, online-markets, resource allocation, and traffic networks.

The seminar is based on the so-called "29th Internet Seminar 2025/26", see
https://www.fan.uni-wuppertal.de/de/lehre/29th-internet-seminar/
The main topics are eventually positive resolvents and semigroups, first in finite dimensional spaces and then in Banach spaces - or to be more precise in Banach lattices, which is a convenient setting for the study of (eventual) positivity.

Seminararbeit und Vortrag über ausgewählte Publikation aus dem Bereich der Visualisierung großer wissenschaftlicher Datensätze

In this course Robust control is introduced. Robust control is an approach to design controllers to deal with uncertainty. The aim is to achieve robust performance (or stability) in the presence of bounded modelling errors.

Many phenomena in nature, in technology, and in economics possess spatial, temporal, or spatio-temporal dynamics. In a probabilistic or statistical modeling framework, such dynamics are expressed by means of dependency models, dependency structures, or dependency measures. These are the topics of the seminar.

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.

Die Veranstaltung findet zusammen mit der FTH-13 statt.
The course will offer a panorama view of Discrete Mathematics, which is a core subject of mathematics with impact on algebra, topology and geometry.
Discrete structures are the main building blocks in algorithm design, and the class will also cover some algorithmic aspects, making it of interest to CS majors. Furthermore, counting techniques and asymptotic estimates are of use in discrete probability, so the class is also suitable for math majors interested in statistics.

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.

Die Veranstaltung findet zusammen mit 03-M-FTH-10 statt.

The course is dedicated to the numerical solution of partial differential equations. The focus is on finite differences and finite element methods.

Partial differential equations are a main component in the modelling of physical, chemical or biological phenomena in several spatial dimensions or in space and time. They also often occur in mathematical problems in geometry or calculus of variations. The lecture deals with the discretisation of partial differential equations and the estimation of the error between continuous and discrete solution. In particular, the finite difference and the finite element method are introduced and investigated. We first discuss the application of the methods to stationary elliptic problems. Later also time-dependent problems are considered. The connection of theory, numerical analysis and implementation is particularly important.

Finding a route that minimizes the travel time from Bremen to another city is easy if all information is available upfront. In reality, when starting the trip we have to decide on a mode of transport and the first parts of our route while information about congestion, and road or train track blockages become available over time. In online optimization, we address such problems where input information is revealed step by step while some parts of the solution are already fixed.

The quantitative assessment and the management of (extreme) risks are key tools for policy makers and stakeholders in many areas such as climate and environmental research, economics, or finance and insurance. In this course, we will get familiar with basic mathematical concepts of (quantitative) risk assessment and management.

Lecture under the specialization
1) Statistics/Stochastics
2) Data Analysis

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.

Die Veranstaltung findet zusammen mit 03-M-FTH-10 statt.

Die Veranstaltung findet zusammen mit der FTH-13 statt.
The course will offer a panorama view of Discrete Mathematics, which is a core subject of mathematics with impact on algebra, topology and geometry.
Discrete structures are the main building blocks in algorithm design, and the class will also cover some algorithmic aspects, making it of interest to CS majors. Furthermore, counting techniques and asymptotic estimates are of use in discrete probability, so the class is also suitable for math majors interested in statistics.

The course is dedicated to the numerical solution of partial differential equations. The focus is on finite differences and finite element methods.

Partial differential equations are a main component in the modelling of physical, chemical or biological phenomena in several spatial dimensions or in space and time. They also often occur in mathematical problems in geometry or calculus of variations. The lecture deals with the discretisation of partial differential equations and the estimation of the error between continuous and discrete solution. In particular, the finite difference and the finite element method are introduced and investigated. We first discuss the application of the methods to stationary elliptic problems. Later also time-dependent problems are considered. The connection of theory, numerical analysis and implementation is particularly important.

Finding a route that minimizes the travel time from Bremen to another city is easy if all information is available upfront. In reality, when starting the trip we have to decide on a mode of transport and the first parts of our route while information about congestion, and road or train track blockages become available over time. In online optimization, we address such problems where input information is revealed step by step while some parts of the solution are already fixed.

The quantitative assessment and the management of (extreme) risks are key tools for policy makers and stakeholders in many areas such as climate and environmental research, economics, or finance and insurance. In this course, we will get familiar with basic mathematical concepts of (quantitative) risk assessment and management.

Lecture under the specialization
1) Statistics/Stochastics
2) Data Analysis

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.

Die Veranstaltung findet zusammen mit 03-M-FTH-10 statt.

Die Veranstaltung findet zusammen mit der FTH-13 statt.
The course will offer a panorama view of Discrete Mathematics, which is a core subject of mathematics with impact on algebra, topology and geometry.
Discrete structures are the main building blocks in algorithm design, and the class will also cover some algorithmic aspects, making it of interest to CS majors. Furthermore, counting techniques and asymptotic estimates are of use in discrete probability, so the class is also suitable for math majors interested in statistics.

The course is dedicated to the numerical solution of partial differential equations. The focus is on finite differences and finite element methods.

Partial differential equations are a main component in the modelling of physical, chemical or biological phenomena in several spatial dimensions or in space and time. They also often occur in mathematical problems in geometry or calculus of variations. The lecture deals with the discretisation of partial differential equations and the estimation of the error between continuous and discrete solution. In particular, the finite difference and the finite element method are introduced and investigated. We first discuss the application of the methods to stationary elliptic problems. Later also time-dependent problems are considered. The connection of theory, numerical analysis and implementation is particularly important.

Finding a route that minimizes the travel time from Bremen to another city is easy if all information is available upfront. In reality, when starting the trip we have to decide on a mode of transport and the first parts of our route while information about congestion, and road or train track blockages become available over time. In online optimization, we address such problems where input information is revealed step by step while some parts of the solution are already fixed.

The quantitative assessment and the management of (extreme) risks are key tools for policy makers and stakeholders in many areas such as climate and environmental research, economics, or finance and insurance. In this course, we will get familiar with basic mathematical concepts of (quantitative) risk assessment and management.

Lecture under the specialization
1) Statistics/Stochastics
2) Data Analysis

The seminar is based on the so-called "29th Internet Seminar 2025/26", see
https://www.fan.uni-wuppertal.de/de/lehre/29th-internet-seminar/
The main topics are eventually positive resolvents and semigroups, first in finite dimensional spaces and then in Banach spaces - or to be more precise in Banach lattices, which is a convenient setting for the study of (eventual) positivity.

The seminar is based on the so-called "29th Internet Seminar 2025/26", see
https://www.fan.uni-wuppertal.de/de/lehre/29th-internet-seminar/
The main topics are eventually positive resolvents and semigroups, first in finite dimensional spaces and then in Banach spaces - or to be more precise in Banach lattices, which is a convenient setting for the study of (eventual) positivity.

Many every-day processes can seen as a game between autonomous interacting players, where each player acts strategically in order to pursue her own objectives. This seminar covers various game-theoretic concepts and techniques, mainly with connections to applications. Use-cases are distributed systems, auctions, online-markets, resource allocation, and traffic networks.

Seminararbeit und Vortrag über ausgewählte Publikation aus dem Bereich der Visualisierung großer wissenschaftlicher Datensätze

In this course Robust control is introduced. Robust control is an approach to design controllers to deal with uncertainty. The aim is to achieve robust performance (or stability) in the presence of bounded modelling errors.

Many phenomena in nature, in technology, and in economics possess spatial, temporal, or spatio-temporal dynamics. In a probabilistic or statistical modeling framework, such dynamics are expressed by means of dependency models, dependency structures, or dependency measures. These are the topics of the seminar.

Die Veranstaltung findet zusammen mit der MKOM-13 statt.
Seminar on selected topics of algebraic topology

Many every-day processes can seen as a game between autonomous interacting players, where each player acts strategically in order to pursue her own objectives. This seminar covers various game-theoretic concepts and techniques, mainly with connections to applications. Use-cases are distributed systems, auctions, online-markets, resource allocation, and traffic networks.

Seminararbeit und Vortrag über ausgewählte Publikation aus dem Bereich der Visualisierung großer wissenschaftlicher Datensätze

In this course Robust control is introduced. Robust control is an approach to design controllers to deal with uncertainty. The aim is to achieve robust performance (or stability) in the presence of bounded modelling errors.

Many phenomena in nature, in technology, and in economics possess spatial, temporal, or spatio-temporal dynamics. In a probabilistic or statistical modeling framework, such dynamics are expressed by means of dependency models, dependency structures, or dependency measures. These are the topics of the seminar.

Die Veranstaltung findet zusammen mit der MKOM-13 statt.
Seminar on selected topics of algebraic topology

Independent study of an advanced selected topic in the area of analysis; can serve as a basis for a Master's thesis.
Please sign in on Stud.IP for the Reading Course in order to obtain up-to-date information on the course.

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.

Die Veranstaltung findet zusammen mit 03-M-FTH-10 statt.

Die Veranstaltung findet zusammen mit der FTH-13 statt.
The course will offer a panorama view of Discrete Mathematics, which is a core subject of mathematics with impact on algebra, topology and geometry.
Discrete structures are the main building blocks in algorithm design, and the class will also cover some algorithmic aspects, making it of interest to CS majors. Furthermore, counting techniques and asymptotic estimates are of use in discrete probability, so the class is also suitable for math majors interested in statistics.

The course is dedicated to the numerical solution of partial differential equations. The focus is on finite differences and finite element methods.

Partial differential equations are a main component in the modelling of physical, chemical or biological phenomena in several spatial dimensions or in space and time. They also often occur in mathematical problems in geometry or calculus of variations. The lecture deals with the discretisation of partial differential equations and the estimation of the error between continuous and discrete solution. In particular, the finite difference and the finite element method are introduced and investigated. We first discuss the application of the methods to stationary elliptic problems. Later also time-dependent problems are considered. The connection of theory, numerical analysis and implementation is particularly important.

Finding a route that minimizes the travel time from Bremen to another city is easy if all information is available upfront. In reality, when starting the trip we have to decide on a mode of transport and the first parts of our route while information about congestion, and road or train track blockages become available over time. In online optimization, we address such problems where input information is revealed step by step while some parts of the solution are already fixed.

The quantitative assessment and the management of (extreme) risks are key tools for policy makers and stakeholders in many areas such as climate and environmental research, economics, or finance and insurance. In this course, we will get familiar with basic mathematical concepts of (quantitative) risk assessment and management.

Lecture under the specialization
1) Statistics/Stochastics
2) Data Analysis

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.

The course is dedicated to the numerical solution of partial differential equations. The focus is on finite differences and finite element methods.

Partial differential equations are a main component in the modelling of physical, chemical or biological phenomena in several spatial dimensions or in space and time. They also often occur in mathematical problems in geometry or calculus of variations. The lecture deals with the discretisation of partial differential equations and the estimation of the error between continuous and discrete solution. In particular, the finite difference and the finite element method are introduced and investigated. We first discuss the application of the methods to stationary elliptic problems. Later also time-dependent problems are considered. The connection of theory, numerical analysis and implementation is particularly important.

Finding a route that minimizes the travel time from Bremen to another city is easy if all information is available upfront. In reality, when starting the trip we have to decide on a mode of transport and the first parts of our route while information about congestion, and road or train track blockages become available over time. In online optimization, we address such problems where input information is revealed step by step while some parts of the solution are already fixed.

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.

Die Veranstaltung findet zusammen mit 03-M-FTH-10 statt.

Die Veranstaltung findet zusammen mit der FTH-13 statt.
The course will offer a panorama view of Discrete Mathematics, which is a core subject of mathematics with impact on algebra, topology and geometry.
Discrete structures are the main building blocks in algorithm design, and the class will also cover some algorithmic aspects, making it of interest to CS majors. Furthermore, counting techniques and asymptotic estimates are of use in discrete probability, so the class is also suitable for math majors interested in statistics.

Finding a route that minimizes the travel time from Bremen to another city is easy if all information is available upfront. In reality, when starting the trip we have to decide on a mode of transport and the first parts of our route while information about congestion, and road or train track blockages become available over time. In online optimization, we address such problems where input information is revealed step by step while some parts of the solution are already fixed.

The quantitative assessment and the management of (extreme) risks are key tools for policy makers and stakeholders in many areas such as climate and environmental research, economics, or finance and insurance. In this course, we will get familiar with basic mathematical concepts of (quantitative) risk assessment and management.

Lecture under the specialization
1) Statistics/Stochastics
2) Data Analysis

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.

The course is dedicated to the numerical solution of partial differential equations. The focus is on finite differences and finite element methods.

Partial differential equations are a main component in the modelling of physical, chemical or biological phenomena in several spatial dimensions or in space and time. They also often occur in mathematical problems in geometry or calculus of variations. The lecture deals with the discretisation of partial differential equations and the estimation of the error between continuous and discrete solution. In particular, the finite difference and the finite element method are introduced and investigated. We first discuss the application of the methods to stationary elliptic problems. Later also time-dependent problems are considered. The connection of theory, numerical analysis and implementation is particularly important.

Finding a route that minimizes the travel time from Bremen to another city is easy if all information is available upfront. In reality, when starting the trip we have to decide on a mode of transport and the first parts of our route while information about congestion, and road or train track blockages become available over time. In online optimization, we address such problems where input information is revealed step by step while some parts of the solution are already fixed.

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.

Die Veranstaltung findet zusammen mit 03-M-FTH-10 statt.

Die Veranstaltung findet zusammen mit der FTH-13 statt.
The course will offer a panorama view of Discrete Mathematics, which is a core subject of mathematics with impact on algebra, topology and geometry.
Discrete structures are the main building blocks in algorithm design, and the class will also cover some algorithmic aspects, making it of interest to CS majors. Furthermore, counting techniques and asymptotic estimates are of use in discrete probability, so the class is also suitable for math majors interested in statistics.

Finding a route that minimizes the travel time from Bremen to another city is easy if all information is available upfront. In reality, when starting the trip we have to decide on a mode of transport and the first parts of our route while information about congestion, and road or train track blockages become available over time. In online optimization, we address such problems where input information is revealed step by step while some parts of the solution are already fixed.

The quantitative assessment and the management of (extreme) risks are key tools for policy makers and stakeholders in many areas such as climate and environmental research, economics, or finance and insurance. In this course, we will get familiar with basic mathematical concepts of (quantitative) risk assessment and management.

Lecture under the specialization
1) Statistics/Stochastics
2) Data Analysis

Many every-day processes can seen as a game between autonomous interacting players, where each player acts strategically in order to pursue her own objectives. This seminar covers various game-theoretic concepts and techniques, mainly with connections to applications. Use-cases are distributed systems, auctions, online-markets, resource allocation, and traffic networks.

Seminararbeit und Vortrag über ausgewählte Publikation aus dem Bereich der Visualisierung großer wissenschaftlicher Datensätze

In this course Robust control is introduced. Robust control is an approach to design controllers to deal with uncertainty. The aim is to achieve robust performance (or stability) in the presence of bounded modelling errors.

Many every-day processes can seen as a game between autonomous interacting players, where each player acts strategically in order to pursue her own objectives. This seminar covers various game-theoretic concepts and techniques, mainly with connections to applications. Use-cases are distributed systems, auctions, online-markets, resource allocation, and traffic networks.

Seminararbeit und Vortrag über ausgewählte Publikation aus dem Bereich der Visualisierung großer wissenschaftlicher Datensätze

In this course Robust control is introduced. Robust control is an approach to design controllers to deal with uncertainty. The aim is to achieve robust performance (or stability) in the presence of bounded modelling errors.

The seminar is based on the so-called "29th Internet Seminar 2025/26", see
https://www.fan.uni-wuppertal.de/de/lehre/29th-internet-seminar/
The main topics are eventually positive resolvents and semigroups, first in finite dimensional spaces and then in Banach spaces - or to be more precise in Banach lattices, which is a convenient setting for the study of (eventual) positivity.

Many phenomena in nature, in technology, and in economics possess spatial, temporal, or spatio-temporal dynamics. In a probabilistic or statistical modeling framework, such dynamics are expressed by means of dependency models, dependency structures, or dependency measures. These are the topics of the seminar.

Die Veranstaltung findet zusammen mit der MKOM-13 statt.
Seminar on selected topics of algebraic topology

The seminar is based on the so-called "29th Internet Seminar 2025/26", see
https://www.fan.uni-wuppertal.de/de/lehre/29th-internet-seminar/
The main topics are eventually positive resolvents and semigroups, first in finite dimensional spaces and then in Banach spaces - or to be more precise in Banach lattices, which is a convenient setting for the study of (eventual) positivity.

Many phenomena in nature, in technology, and in economics possess spatial, temporal, or spatio-temporal dynamics. In a probabilistic or statistical modeling framework, such dynamics are expressed by means of dependency models, dependency structures, or dependency measures. These are the topics of the seminar.

Die Veranstaltung findet zusammen mit der MKOM-13 statt.
Seminar on selected topics of algebraic topology

Das Seminar findet im Neos Gebäude statt. Raum nach Absprache.
Students study special topics of numerical mathematics in this reading course. The aim is a self-study of selected topics on the basis of textbooks, scientific articles or other monographs.

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.

The course is dedicated to the numerical solution of partial differential equations. The focus is on finite differences and finite element methods.

Partial differential equations are a main component in the modelling of physical, chemical or biological phenomena in several spatial dimensions or in space and time. They also often occur in mathematical problems in geometry or calculus of variations. The lecture deals with the discretisation of partial differential equations and the estimation of the error between continuous and discrete solution. In particular, the finite difference and the finite element method are introduced and investigated. We first discuss the application of the methods to stationary elliptic problems. Later also time-dependent problems are considered. The connection of theory, numerical analysis and implementation is particularly important.

Finding a route that minimizes the travel time from Bremen to another city is easy if all information is available upfront. In reality, when starting the trip we have to decide on a mode of transport and the first parts of our route while information about congestion, and road or train track blockages become available over time. In online optimization, we address such problems where input information is revealed step by step while some parts of the solution are already fixed.

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.

Die Veranstaltung findet zusammen mit 03-M-FTH-10 statt.

Die Veranstaltung findet zusammen mit der FTH-13 statt.
The course will offer a panorama view of Discrete Mathematics, which is a core subject of mathematics with impact on algebra, topology and geometry.
Discrete structures are the main building blocks in algorithm design, and the class will also cover some algorithmic aspects, making it of interest to CS majors. Furthermore, counting techniques and asymptotic estimates are of use in discrete probability, so the class is also suitable for math majors interested in statistics.

Finding a route that minimizes the travel time from Bremen to another city is easy if all information is available upfront. In reality, when starting the trip we have to decide on a mode of transport and the first parts of our route while information about congestion, and road or train track blockages become available over time. In online optimization, we address such problems where input information is revealed step by step while some parts of the solution are already fixed.

The quantitative assessment and the management of (extreme) risks are key tools for policy makers and stakeholders in many areas such as climate and environmental research, economics, or finance and insurance. In this course, we will get familiar with basic mathematical concepts of (quantitative) risk assessment and management.

Lecture under the specialization
1) Statistics/Stochastics
2) Data Analysis

Die Veranstaltung findet zusammen mit 03-M-FTH-10 statt.

Finding a route that minimizes the travel time from Bremen to another city is easy if all information is available upfront. In reality, when starting the trip we have to decide on a mode of transport and the first parts of our route while information about congestion, and road or train track blockages become available over time. In online optimization, we address such problems where input information is revealed step by step while some parts of the solution are already fixed.

The quantitative assessment and the management of (extreme) risks are key tools for policy makers and stakeholders in many areas such as climate and environmental research, economics, or finance and insurance. In this course, we will get familiar with basic mathematical concepts of (quantitative) risk assessment and management.

Lecture under the specialization
1) Statistics/Stochastics
2) Data Analysis

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.

Die Veranstaltung findet zusammen mit der FTH-13 statt.
The course will offer a panorama view of Discrete Mathematics, which is a core subject of mathematics with impact on algebra, topology and geometry.
Discrete structures are the main building blocks in algorithm design, and the class will also cover some algorithmic aspects, making it of interest to CS majors. Furthermore, counting techniques and asymptotic estimates are of use in discrete probability, so the class is also suitable for math majors interested in statistics.

The course is dedicated to the numerical solution of partial differential equations. The focus is on finite differences and finite element methods.

Partial differential equations are a main component in the modelling of physical, chemical or biological phenomena in several spatial dimensions or in space and time. They also often occur in mathematical problems in geometry or calculus of variations. The lecture deals with the discretisation of partial differential equations and the estimation of the error between continuous and discrete solution. In particular, the finite difference and the finite element method are introduced and investigated. We first discuss the application of the methods to stationary elliptic problems. Later also time-dependent problems are considered. The connection of theory, numerical analysis and implementation is particularly important.

Finding a route that minimizes the travel time from Bremen to another city is easy if all information is available upfront. In reality, when starting the trip we have to decide on a mode of transport and the first parts of our route while information about congestion, and road or train track blockages become available over time. In online optimization, we address such problems where input information is revealed step by step while some parts of the solution are already fixed.

Die Veranstaltung findet zusammen mit 03-M-FTH-10 statt.

Finding a route that minimizes the travel time from Bremen to another city is easy if all information is available upfront. In reality, when starting the trip we have to decide on a mode of transport and the first parts of our route while information about congestion, and road or train track blockages become available over time. In online optimization, we address such problems where input information is revealed step by step while some parts of the solution are already fixed.

The quantitative assessment and the management of (extreme) risks are key tools for policy makers and stakeholders in many areas such as climate and environmental research, economics, or finance and insurance. In this course, we will get familiar with basic mathematical concepts of (quantitative) risk assessment and management.

Lecture under the specialization
1) Statistics/Stochastics
2) Data Analysis

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.

Die Veranstaltung findet zusammen mit der FTH-13 statt.
The course will offer a panorama view of Discrete Mathematics, which is a core subject of mathematics with impact on algebra, topology and geometry.
Discrete structures are the main building blocks in algorithm design, and the class will also cover some algorithmic aspects, making it of interest to CS majors. Furthermore, counting techniques and asymptotic estimates are of use in discrete probability, so the class is also suitable for math majors interested in statistics.

The course is dedicated to the numerical solution of partial differential equations. The focus is on finite differences and finite element methods.

Partial differential equations are a main component in the modelling of physical, chemical or biological phenomena in several spatial dimensions or in space and time. They also often occur in mathematical problems in geometry or calculus of variations. The lecture deals with the discretisation of partial differential equations and the estimation of the error between continuous and discrete solution. In particular, the finite difference and the finite element method are introduced and investigated. We first discuss the application of the methods to stationary elliptic problems. Later also time-dependent problems are considered. The connection of theory, numerical analysis and implementation is particularly important.

Finding a route that minimizes the travel time from Bremen to another city is easy if all information is available upfront. In reality, when starting the trip we have to decide on a mode of transport and the first parts of our route while information about congestion, and road or train track blockages become available over time. In online optimization, we address such problems where input information is revealed step by step while some parts of the solution are already fixed.

Many phenomena in nature, in technology, and in economics possess spatial, temporal, or spatio-temporal dynamics. In a probabilistic or statistical modeling framework, such dynamics are expressed by means of dependency models, dependency structures, or dependency measures. These are the topics of the seminar.

Many phenomena in nature, in technology, and in economics possess spatial, temporal, or spatio-temporal dynamics. In a probabilistic or statistical modeling framework, such dynamics are expressed by means of dependency models, dependency structures, or dependency measures. These are the topics of the seminar.

Many every-day processes can seen as a game between autonomous interacting players, where each player acts strategically in order to pursue her own objectives. This seminar covers various game-theoretic concepts and techniques, mainly with connections to applications. Use-cases are distributed systems, auctions, online-markets, resource allocation, and traffic networks.

The seminar is based on the so-called "29th Internet Seminar 2025/26", see
https://www.fan.uni-wuppertal.de/de/lehre/29th-internet-seminar/
The main topics are eventually positive resolvents and semigroups, first in finite dimensional spaces and then in Banach spaces - or to be more precise in Banach lattices, which is a convenient setting for the study of (eventual) positivity.

Seminararbeit und Vortrag über ausgewählte Publikation aus dem Bereich der Visualisierung großer wissenschaftlicher Datensätze

In this course Robust control is introduced. Robust control is an approach to design controllers to deal with uncertainty. The aim is to achieve robust performance (or stability) in the presence of bounded modelling errors.

Die Veranstaltung findet zusammen mit der MKOM-13 statt.
Seminar on selected topics of algebraic topology

Many every-day processes can seen as a game between autonomous interacting players, where each player acts strategically in order to pursue her own objectives. This seminar covers various game-theoretic concepts and techniques, mainly with connections to applications. Use-cases are distributed systems, auctions, online-markets, resource allocation, and traffic networks.

The seminar is based on the so-called "29th Internet Seminar 2025/26", see
https://www.fan.uni-wuppertal.de/de/lehre/29th-internet-seminar/
The main topics are eventually positive resolvents and semigroups, first in finite dimensional spaces and then in Banach spaces - or to be more precise in Banach lattices, which is a convenient setting for the study of (eventual) positivity.

Seminararbeit und Vortrag über ausgewählte Publikation aus dem Bereich der Visualisierung großer wissenschaftlicher Datensätze

In this course Robust control is introduced. Robust control is an approach to design controllers to deal with uncertainty. The aim is to achieve robust performance (or stability) in the presence of bounded modelling errors.

Die Veranstaltung findet zusammen mit der MKOM-13 statt.
Seminar on selected topics of algebraic topology

Die Veranstaltung findet zusammen mit 03-M-FTH-10 statt.

Finding a route that minimizes the travel time from Bremen to another city is easy if all information is available upfront. In reality, when starting the trip we have to decide on a mode of transport and the first parts of our route while information about congestion, and road or train track blockages become available over time. In online optimization, we address such problems where input information is revealed step by step while some parts of the solution are already fixed.

The quantitative assessment and the management of (extreme) risks are key tools for policy makers and stakeholders in many areas such as climate and environmental research, economics, or finance and insurance. In this course, we will get familiar with basic mathematical concepts of (quantitative) risk assessment and management.

Lecture under the specialization
1) Statistics/Stochastics
2) Data Analysis

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.

Die Veranstaltung findet zusammen mit der FTH-13 statt.
The course will offer a panorama view of Discrete Mathematics, which is a core subject of mathematics with impact on algebra, topology and geometry.
Discrete structures are the main building blocks in algorithm design, and the class will also cover some algorithmic aspects, making it of interest to CS majors. Furthermore, counting techniques and asymptotic estimates are of use in discrete probability, so the class is also suitable for math majors interested in statistics.

The course is dedicated to the numerical solution of partial differential equations. The focus is on finite differences and finite element methods.

Partial differential equations are a main component in the modelling of physical, chemical or biological phenomena in several spatial dimensions or in space and time. They also often occur in mathematical problems in geometry or calculus of variations. The lecture deals with the discretisation of partial differential equations and the estimation of the error between continuous and discrete solution. In particular, the finite difference and the finite element method are introduced and investigated. We first discuss the application of the methods to stationary elliptic problems. Later also time-dependent problems are considered. The connection of theory, numerical analysis and implementation is particularly important.

Finding a route that minimizes the travel time from Bremen to another city is easy if all information is available upfront. In reality, when starting the trip we have to decide on a mode of transport and the first parts of our route while information about congestion, and road or train track blockages become available over time. In online optimization, we address such problems where input information is revealed step by step while some parts of the solution are already fixed.

Weitere Informationen in Stud.IP.

Weitere Informationen in Stud.IP.

2. Semesterhälfte
Parallele 1: Di 14-19.30 Uhr
Parallele 2: Mi 14-19.30 Uhr
Parallele 3: Do 14-19.30 Uhr

1. Semesterhälfte

2. Semesterhälfte
Parallele 1: Di 14-19 Uhr
Parallele 2: Mi 14-19 Uhr
Parallele 3: Fr 10-15 Uhr

"Informationen zum Modul Allgemeine Chemie"
https://www.uni-bremen.de/fileadmin/user_upload/fachbereiche/fb2/marchem/alc_infotext_2526.pdf

"Informationen zum Modul Allgemeine Chemie"
https://www.uni-bremen.de/fileadmin/user_upload/fachbereiche/fb2/marchem/alc_infotext_2526.pdf

"Informationen zum Modul Allgemeine Chemie"
https://www.uni-bremen.de/fileadmin/user_upload/fachbereiche/fb2/marchem/alc_infotext_2526.pdf
Gruppeneinteilung und weitere Infos in Stud.IP.

SWS 10

https://lvb.informatik.uni-bremen.de/ibap/03-ibap-bs.pdf

Schwerpunkt: DMI, VMC
https://lvb.informatik.uni-bremen.de/ibap/03-ibap-cg.pdf
Programmierkenntnisse sind Voraussetzung (ein erfolgreicher Abschluss des "Propädeutikums C" wird empfohlen), ebenso wie algorithmisches Denken, eine gewisse Vertrautheit mit mathematischer Begriffsbildung und Vorgehensweise.

Diese Vorlesung soll sowohl eine Einführung in die theoretischen und methodischen Grundlagen der Computergraphik geben, als auch die Grundlagen für die praktische Implementierung von computergraphischen Systemen legen. Der Schwerpunkt liegt auf Algorithmen und Konzepten zur Repräsentation und Visualisierung von polygonalen, 3-dimensionalen graphischen Szenen.
Der Inhalt umfasst in der Regel folgende Themen:
Mathematische Grundlagen; OpenGL and C ; 2D Algorithmen der Computergrafik (Scan Conversion, Visibility Computations, etc.); Theorie der Farben, Farbräume (hauptsächlich physikalische, neurologische, und technische Aspekte); 3D Computergraphik (Rendering Pipeline, Transformationen, Beleuchtung, etc.); Techniken zum Echtzeit-Rendering; Das Konzept und die Programmierung von Shadern; Texturierung (Einordnung in die Pipeline, einfache Parametrisierung, etc.).

Die Übungsaufgaben werden teils theoretisch, teils praktisch sein, wobei die praktischen Aufgaben gewisse Programmierfähigkeiten in C verlangen. (Zu Beginn der Vorlesung wird deshalb nochmals ein kurzer "Refresh" Ihrer C/C-Kenntnisse gemacht.) Die Vorlesung setzt eine gewisse mathematische, algorithmische und programmiertechnische Gewandtheit voraus, fördert diese aber auch und führt sie weiter.
https://cgvr.cs.uni-bremen.de/teaching/

Die "Hauptveranstaltung" Datenbanksysteme mit 6 CP geht bis Ende Dezember und
die 3CP Ergänzung Datenbanksysteme beginnt im Januar.
https://lvb.informatik.uni-bremen.de/ibap/03-ibap-dbs.pdf

Schwerpunkt: SQ
https://lvb.informatik.uni-bremen.de/ibap/03-ibap-isec.pdf

https://lvb.informatik.uni-bremen.de/ibap/03-ibap-ra.pdf

Schwerpunkt: VMC
https://lvb.informatik.uni-bremen.de/ibap/03-ibap-sdv.pdf

• Was macht Sensordaten anders als anderen Daten?
• Kamera, Mikrophon, Inertialsensor als drei wichtige Sensoren und was sie messen
• Algorithmen zur Analyse von Sensordaten (z.B. Fouriertransformation, Sprachmerkmale, farbgetriebene BV, Filte, Houghtransformation, Bewegungsmerkmale, Klassifizierungsalgorithmen)
• Entwicklungs- und Evaluationsmethoden für Systeme mit Sensordaten
• Bayesschätzer und -filter

Die Vorlesung wird als Video zur Verfügung gestellt. In den Präsenzterminen wird der Stoff wiederholt und eingeübt. Dazu gibt es unbenotete Hausaufgaben als Vorbereitung. Die Prüfungsleistung ist eine Klausur.

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/

Profil: KIKR
Schwerpunkt: IMAP-AI, IMA-VMC
https://lvb.informatik.uni-bremen.de/imap/03-imap-aml.pdf

Schwerpunkt: IMK-AI, IMA-VMC
https://lvb.informatik.uni-bremen.de/imap/03-imap-amai.pdf

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.

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/

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.

Profil: KIKR
Schwerpunkt: IMVA-AI
https://lvb.informatik.uni-bremen.de/imva/03-imva-gpmlr.pdf

Profil: SQ, DMI
Schwerpunkt: IMA-SQ, IMA-AI, IMVP-DMI
https://lvb.informatik.uni-bremen.de/imaa/03-imaa-itmds.pdf

Profil: KIKR, DMI
Schwerpunkt: IMVA-DMI, IMVA-AI
https://lvb.informatik.uni-bremen.de/imaa/03-imaa-stmw.pdf

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.

Profil: SQ
Schwerpunkt: IMA-SQ.
https://lvb.informatik.uni-bremen.de/imat/03-imat-krypt.pdf
mit Zusatzleistung(en) (wird in der Veranstaltung bekannt gegeben) 9 CP für Studierende in den mathematischen Studiengängen

Profil: SQ, DMI
Schwerpunkt: IMA-SQ, IMA-AI, IMVP-DMI
https://lvb.informatik.uni-bremen.de/imaa/03-imaa-itmds.pdf

Profil: SQ
Schwerpunkt: IMA-SQ, IMVP-VMC
https://lvb.informatik.uni-bremen.de/imap/03-imap-swre.pdf

Profil: SQ.
Schwerpunkt: IMAP-SQ
https://lvb.informatik.uni-bremen.de/imap/03-imap-ta.pdf

Profil: KIKR
Schwerpunkt: IMAP-AI, IMA-VMC
https://lvb.informatik.uni-bremen.de/imap/03-imap-aml.pdf

Schwerpunkt: IMK-AI, IMA-VMC
https://lvb.informatik.uni-bremen.de/imap/03-imap-amai.pdf

Profil: KIKR
Schwerpunkt: IMVP-AI, IMVP-VMC
https://lvb.informatik.uni-bremen.de/imvp/03-imvp-bcod.pdf

Profil: SQ, DMI.
Schwerpunkt: IMVP-SQ, IMVP-DMI, IMVP-VMC
https://lvb.informatik.uni-bremen.de/imap/03-imap-rnmn.pdf

Profil: KIKR
Schwerpunkt: IMVP-VMC, IMVP-AI
https://lvb.informatik.uni-bremen.de/imvp/03-imvp-sprs.pdf
Die Vorlesung findet online per Zoom statt.

Profil: SQ
Schwerpunkt: IMA-SQ, IMVP-VMC
https://lvb.informatik.uni-bremen.de/imap/03-imap-swre.pdf

Profil SQ
Schwerpunkt: IMK-SQ , IMVP-VMC
https://lvb.informatik.uni-bremen.de/imap/03-imap-shsq.pdf

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/

Profil: SQ
Schwerpunkt: IMVP-SQ
https://lvb.informatik.uni-bremen.de/imvp/03-imvp-dls.pdf
Die Übung der Veranstaltung findet am Dienstag in Raum MZH 2340 statt.

Profil: SQ, DMI.
Schwerpunkt: IMVP-SQ, IMVP-DMI, IMVP-VMC
https://lvb.informatik.uni-bremen.de/imap/03-imap-rnmn.pdf

Profil: SQ
Schwerpunkt: IMA-SQ, IMVP-VMC
https://lvb.informatik.uni-bremen.de/imap/03-imap-swre.pdf

Profil: SQ.
Schwerpunkt: IMAP-SQ
https://lvb.informatik.uni-bremen.de/imap/03-imap-ta.pdf

Profil: SQ
Schwerpunkt: IMA-SQ.
https://lvb.informatik.uni-bremen.de/imat/03-imat-krypt.pdf
mit Zusatzleistung(en) (wird in der Veranstaltung bekannt gegeben) 9 CP für Studierende in den mathematischen Studiengängen

Profil: SQ
Schwerpunkt: IMVT-SQ
https://lvb.informatik.uni-bremen.de/imat/03-imat-irq.pdf

Schwerpunkt: IMK-AI, IMA-VMC
https://lvb.informatik.uni-bremen.de/imap/03-imap-amai.pdf

Profil: KIKR
Schwerpunkt: IMAP-AI, IMA-VMC
https://lvb.informatik.uni-bremen.de/imap/03-imap-aml.pdf

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.

Profil: SQ, DMI.
Schwerpunkt: IMA-DMI, IMVA-SQ
https://lvb.informatik.uni-bremen.de/imaa/03-imaa-mitr.pdf

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.

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/

Schwerpunkt: IMVP-AI, IMVP-DMI
https://lvb.informatik.uni-bremen.de/imvp/03-imvp-ecl.pdf

Profil: SQ, DMI.
Schwerpunkt: IMVP-SQ, IMVP-DMI, IMVP-VMC
https://lvb.informatik.uni-bremen.de/imap/03-imap-rnmn.pdf

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/

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.

Profil: SQ, DMI
Schwerpunkt: IMA-SQ, IMA-AI, IMVP-DMI
https://lvb.informatik.uni-bremen.de/imaa/03-imaa-itmds.pdf

Profil: SQ, DMI.
Schwerpunkt: IMA-DMI, IMVA-SQ
https://lvb.informatik.uni-bremen.de/imaa/03-imaa-mitr.pdf

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.

Profil: KIKR, DMI
Schwerpunkt: IMVA-DMI, IMVA-AI
https://lvb.informatik.uni-bremen.de/imaa/03-imaa-stmw.pdf

Profil SQ
Schwerpunkt: IMK-SQ , IMVP-VMC
https://lvb.informatik.uni-bremen.de/imap/03-imap-shsq.pdf

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/

Profil: SQ, DMI
Schwerpunkt: IMA-SQ, IMA-AI, IMVP-DMI
https://lvb.informatik.uni-bremen.de/imaa/03-imaa-itmds.pdf

Profil: SQ, DMI.
Schwerpunkt: IMA-DMI, IMVA-SQ
https://lvb.informatik.uni-bremen.de/imaa/03-imaa-mitr.pdf

Profil: SQ.
Schwerpunkt: IMAP-SQ
https://lvb.informatik.uni-bremen.de/imap/03-imap-ta.pdf

Profil: KIKR
Schwerpunkt: IMAP-AI, IMA-VMC
https://lvb.informatik.uni-bremen.de/imap/03-imap-aml.pdf

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.

Profil KIKR
Schwerpunkt: IMA-AI
Modultyp C (6 CP) im Studiengang Language Sciences M.A.
https://lvb.informatik.uni-bremen.de/imap/03-imap-ase.pdf

Die Vorlesungsinhalte werden über Videos und Folien asynchron bereitgestellt ("flipped classroom"-Konzept). Darüber hinaus gibt es einen Präsenz-Termin am Dienstag. Dieser Präsenz-Termin ist als "Interaktives Repititorium" gestaltet und wird nicht aufgezeichnet. Donnerstags finden im Zwei-Wochen-Rhythmus Übungen statt.

Der Kurs "Automatische Spracherkennung" bietet eine Einführung in die automatische Spracherkennung. In diesem Kurs werden die Sprachverarbeitung beim Menschen, Signalverarbeitung, statistische Modellierung von Sprache sowie die wesentlichen praktischen Ansätze und Methoden für den Einsatz automatischer Spracherkennung behandelt.

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

Profil: KIKR
Schwerpunkt: IMA-AI
https://lvb.informatik.uni-bremen.de/imap/03-imap-iis.pdf
Die Vorlesung findet asynchron und die Übung online statt.

Profil: SQ, DMI
Schwerpunkt: IMA-SQ, IMA-AI, IMVP-DMI
https://lvb.informatik.uni-bremen.de/imaa/03-imaa-itmds.pdf

Profil: KIKR
Schwerpunkt: IMAP-AI, IMA-VMC
https://lvb.informatik.uni-bremen.de/imap/03-imap-aml.pdf

Schwerpunkt: IMVP-AI
https://lvb.informatik.uni-bremen.de/imvp/03-imvp-air.pdf
Die Veranstaltung findet im DFKI statt.

Profil KIKR
Schwerpunkt: IMA-AI
Modultyp C (6 CP) im Studiengang Language Sciences M.A.
https://lvb.informatik.uni-bremen.de/imap/03-imap-ase.pdf

Die Vorlesungsinhalte werden über Videos und Folien asynchron bereitgestellt ("flipped classroom"-Konzept). Darüber hinaus gibt es einen Präsenz-Termin am Dienstag. Dieser Präsenz-Termin ist als "Interaktives Repititorium" gestaltet und wird nicht aufgezeichnet. Donnerstags finden im Zwei-Wochen-Rhythmus Übungen statt.

Der Kurs "Automatische Spracherkennung" bietet eine Einführung in die automatische Spracherkennung. In diesem Kurs werden die Sprachverarbeitung beim Menschen, Signalverarbeitung, statistische Modellierung von Sprache sowie die wesentlichen praktischen Ansätze und Methoden für den Einsatz automatischer Spracherkennung behandelt.

Profil: KIKR
Schwerpunkt: IMVP-AI, IMVP-VMC
https://lvb.informatik.uni-bremen.de/imvp/03-imvp-bcod.pdf

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

Schwerpunkt: IMVP-AI, IMVP-DMI
https://lvb.informatik.uni-bremen.de/imvp/03-imvp-ecl.pdf

Profil: KIKR
Schwerpunkt: IMVP-AI
https://lvb.informatik.uni-bremen.de/imvp/03-imvp-gme.pdf
Termine: 10-tägiger Blockkurs nach der Vorlesungszeit.

Wird als hybrider Blockkurs nach der Vorlesungszeit angeboten. Bei Interesse frühzeitig bei felix.putzeprotect me ?!uni-bremenprotect me ?!.de anmelden, da begrenzte Teilnehmer:innen-Zahl. Eine Anmeldung nur über StudIP ist nicht ausreichend.

Profil: KIKR
Schwerpunkt: IMA-AI
https://lvb.informatik.uni-bremen.de/imap/03-imap-iis.pdf
Die Vorlesung findet asynchron und die Übung online statt.

Profil: KIKR
Schwerpunkt: IMVP- AI
https://lvb.informatik.uni-bremen.de/imvp/03-imvp-mlar.pdf
Die Veranstaltung findet in den Räumen des DFKI statt.

Profil: KIKR
Schwerpunkt: IMVP-VMC, IMVP-AI
https://lvb.informatik.uni-bremen.de/imvp/03-imvp-sprs.pdf
Die Vorlesung findet online per Zoom statt.

https://lvb.informatik.uni-bremen.de/imvp/03-imvp-tcrs.pdf
Schwerpunkt: IMVP-AI

http//:www.uni-bremen.de/finpol

httP://www.lsw-bremen.de

http://www.uni-bremen.de/controlling

http://makro.uni-bremen.de

http://www.lsw-bremen.de

http://www.lsw-bremen.de

http://www.lemex.uni-bremen.de

http://www.lemex.uni-bremen.de

http://www.fiwi.uni-bremen.de

http://www.uni-bremen.de/fiwi/

http://www.innovation.uni-bremen.de

Bitte beachten Sie die Veranstaltungszeiten im Ablaufplan.

http://www.uni-bremen.de/en/img/teaching/master-studies

Bitte beachten Sie die Veranstaltungszeiten im Ablaufplan.

http://www.uni-bremen.de/markstones/lehre/masterstudium