Modules

58 results

B Elective Modules58

Advanced Deep Learning for Computer Vision: Visual ComputingNo ratings for this module yet.B1.2, B2.2The module conveys current deep-learning methods for computer vision. You will learn both theoretical foundations of modern neural architectures and practical methods such as generative models (GANs, diffusion models, Large Reconstruction Models) and modern 3D representations (e.g., Neural Radiance Fields, 3D Gaussian Splatting). In the end you will be able to apply, evaluate, and implement state-of-the-art methods in project work.8 ECTSruns this semesterIN2390Advanced Deep Learning for RoboticsNo ratings for this module yet.B1.2, B2.2In this module you deepen advanced deep learning methods with a focus on robotic applications and deep reinforcement learning. You learn both theoretical foundations of modern network architectures and probabilistic methods as well as their practical implementation in simulations and projects for robotics tasks.8 ECTSruns this semesterCIT433027Approximate Dynamic Programming and Reinforcement LearningNo ratings for this module yet.B1.2, B2.2You will learn methods of Approximate Dynamic Programming (ADP) and Reinforcement Learning (RL) to solve sequential decision problems. In the end you will be able to describe fundamental models and algorithms, follow derivations, and implement simple ADP/RL methods and apply them to simple tasks (e.g., robotic).6 ECTSruns this semesterEI7649Computer Vision III: Detektion, Segmentierung und TrackingNo ratings for this module yet.B1.2, B2.2You will learn modern methods for object recognition, segmentation and tracking in images and videos. In the end you will understand the underlying deep-learning concepts and be able to work on real computer-vision problems with state-of-the-art models in PyTorch.6 ECTSruns this semesterIN2375Efficient Algorithms and Data StructuresNo ratings for this module yet.B1.2, B2.2You will learn the fundamentals of analyzing algorithms as well as central data structures and fundamental algorithmic problems. The focus is on runtime and space analysis, various search trees, hashing methods, priority queues, union-find structures, as well as maxflow/mincut and matching algorithms. In the end you will be able to analyze algorithms, assess the efficiency of data structures, and design new solutions for problems.8 ECTSruns this semesterIN2003
53 more in B Elective ModulesEinführung in Quantum ComputingNo ratings for this module yet.B1.2, B2.2You will learn the mathematical foundations of Quantum Computing as well as the basic concepts of quantum mechanics and quantum circuits. In the end you will be able to analyze simple quantum algorithms, design and assess quantum circuits for fundamental tasks, and understand how quantum computers may be used in the future.5 ECTSruns this semesterIN2381Foundations and Application of Generative AINo ratings for this module yet.B1.2, B2.2You will learn the fundamentals and practical applications of generative AI, including modern models such as transformer architectures, Large Language Models, and Stable Diffusion. In the end you will be able to apply prompt engineering, load open-source models and fine-tune them, as well as assess opportunities, risks, and security aspects of generative AI.6 ECTSruns this semesterCITHN2014Introduction to Deep LearningNo ratings for this module yet.B1.2, B2.2In this module you will learn the fundamentals and current methods of Deep Learning, with a special focus on neural networks and Convolutional Neural Networks. You understand theory (e.g. backpropagation, SGD, regularization) and acquire practical experience in training and optimizing network architectures, so you can solve simple applications such as digit recognition or image classification.6 ECTSruns this semesterIN2346Introduction to Deep Reinforcement LearningNo ratings for this module yet.B1.2, B2.2You learn the theory and fundamentals of Deep Reinforcement Learning (DRL) as well as relevant deep-learning and reinforcement-learning concepts. By the end you will be able to model problems as Markov Decision Processes, understand and apply DRL algorithms, and assess their advantages and disadvantages.6 ECTSruns this semesterMGT001299Künstliche Intelligenz in der MedizinNo ratings for this module yet.B1.2, B2.2You will learn the fundamentals and current methods of Artificial Intelligence in the medical context, from ML for medical imaging through NLP for clinical data to data protection, interpretability and ethical aspects. In the end you can classify the most important topics, apply them to your own deep-learning projects and develop strategies for evaluation and implementation in clinical practice.5 ECTSruns this semesterIN2403Large DeviationsNo ratings for this module yet.B1.2, B2.2You will learn the theory of large deviations, which describes how unlikely events occur in probability models and how quickly their probabilities decay. In the end you will be able to apply fundamental techniques of large-deviation theory and understand applications such as for sums of random variables and empirical distributions.5 ECTSruns this semesterMA5417Machine Learning for 3D GeometryNo ratings for this module yet.B1.2, B2.2You will learn theoretical foundations and modern machine‑learning methods for 3D geometric data. The module covers representations of shapes and scenes as well as deep‑learning architectures for discriminative and generative tasks such as classification, segmentation, reconstruction and synthesis. In the end you will be able to understand and practically apply common approaches to point clouds, volumetric data, multi‑view inputs and graphs.6 ECTSruns this semesterIN2392Multilinear AlgebraNo ratings for this module yet.B1.2, B2.2You will learn concepts and tools of multilinear algebra and apply them, in particular in connection with matrix analysis and matrix algebra. In the end you will be able to understand tensor products, Kronecker operations and related structures and use them in mathematical contexts.5 ECTSruns this semesterCIT413063Natural Language ProcessingNo ratings for this module yet.B1.2, B2.2You will receive a solid introduction to modern Natural Language Processing (NLP) methods. In the end you will know central concepts, algorithms and models from tokenizing, through parsing, embeddings and NER, to modern neural approaches and you will be able to read, analyze and contextualize scientific publications in the discipline for your own projects or theses.6 ECTSruns this semesterIN2361Nonconvex Global OptimizationNo ratings for this module yet.B1.2, B2.2You will learn methods of global optimization for nonconvex and possibly nonsmooth objective functions and how to apply them. Beginning with (stochastic) gradient methods and simulated annealing, you walk toward multi‑particle methods such as Particle Swarm Optimization (PSO) and Consensus‑Based Optimization (CBO) and understand their global convergence properties.6 ECTSruns this semesterCIT4130019Probabilistische Techniken und Algorithmen in der DatenanalyseNo ratings for this module yet.B1.2, B2.2You will learn probabilistic techniques and algorithms used in data analysis for dimensionality reduction and data recovery from incomplete information. In the end, you will understand the basics of random matrices, assess randomized algorithms, and apply and analyze methods such as JL embeddings, compressed sensing, and randomness-based matrix/tensor reconstruction.6 ECTSruns this semesterMA4803Trustworthy Machine Learning SystemsNo ratings for this module yet.B1.2, B2.2You learn how to design and evaluate systems that provide trustworthy functions with machine-learning components. In the end you will be able to assess the necessity, benefits and challenges of such systems in various application fields, as well as analyze risks and derive appropriate measures to create trustworthy ML components.3 ECTSruns this semesterCIT4330017Visual Data AnalyticsNo ratings for this module yet.B1.2, B2.2You will learn the entire visualization pipeline — from data acquisition and preprocessing over interpolation and filtering to presentation. You understand methods of information and scientific visualization for 2D/3D scalar and vector fields as well as terrain rendering and can evaluate and apply suitable techniques.5 ECTSruns this semesterIN2026Advanced Deep Learning for Computer Vision: Dynamic VisionNo ratings for this module yet.B1.2, B2.2You will learn advanced deep-learning methods with a clear focus on video analysis for computer-vision tasks. Beyond the theoretical foundations, you will train and implement neural networks yourself and work on a semester-long project on current research topics of the group.8 ECTSno date this semesterIN2389Advanced Machine Learning: Deep Generative ModelsNo ratings for this module yet.B1.2, B2.2You will engage with advanced methods of machine learning, with a focus on deep generative models. In the end you will know the theoretical foundations and be able to apply and implement the key building blocks (Normalizing Flows, VAEs, GANs, diffusion models) in a modern programming language and qualitatively compare them.3 ECTSno date this semesterCIT4230003Advanced Natural Language ProcessingNo ratings for this module yet.B1.2, B2.2You engage with current, advanced topics in Natural Language Processing: modern transformer models and explainability, machine translation for resource-poor languages, argument mining and ethical aspects, dialogue-oriented AI, quantum NLP, automatic text summarization as well as multimodal models (text + images). In the end you will be able to understand research work on these methods, combine technical building blocks and design and evaluate own architectural variants for research or practical application.5 ECTSno date this semesterCIT4230002Advanced Topics in Uncertainty QuantificationNo ratings for this module yet.B1.2, B2.2You will learn methods for uncertainties quantification for sensitivity analyses, estimation of rare events, and the Bayesian approach to inverse problems. In the end you will be able to select appropriate numerical and statistical solution procedures and critically assess their foundations as well as their limitations.6 ECTSno date this semesterCIT4130021Algorithmen für Uncertainty QuantificationNo ratings for this module yet.B1.2, B2.2You will learn methods for quantifying uncertainties in computer-based simulations. In the end you will be able to place central algorithms for Forward Uncertainty Quantification, assess their complexity, and evaluate when which procedures (e.g., Monte Carlo, Quasi-Monte Carlo, stochastic collocation, stochastic Galerkin) are suitable.5 ECTSno date this semesterIN2345Algorithmic Game TheoryNo ratings for this module yet.B1.2, B2.2You will learn the fundamentals of algorithmic game theory at the intersection of computer science, mathematics, and economics. In this module you will deal with algorithmic aspects of game-theoretic solution concepts such as Nash equilibria and with the design of economic mechanisms; in the end you will be able to analyze these concepts algorithmically and in terms of complexity theory.5 ECTSno date this semesterIN2239Algorithms for Scientific ComputingNo ratings for this module yet.B1.2, B2.2You will learn efficient, hierarchical algorithms and data structures for scientific computing and how to implement them. The focus is on fast discrete Fourier and related transforms (FFT, DCT/DST), space-filling curves (Peano, Hilbert) for organizing multi-dimensional data, as well as hierarchical methods such as Sparse Grids and adaptive representations. In the end you will be able to explain such procedures, analyze them, and implement them if needed.8 ECTSno date this semesterIN2001Algorithms for Scientific Computing IINo ratings for this module yet.B1.2, B2.2You engage with advanced numerical methods and their application in scientific computing. Depending on the lecture focus, you learn e.g. efficient procedures for sparsely populated matrices, numerical techniques for quantum systems, or methods such as molecular dynamics, sparse grids and algebraic multigrid. In the end you can apply suitable methods to demanding application problems and explain and utilize their hierarchical aspects.4 ECTSno date this semesterIN2002Applied Reinforcement LearningNo ratings for this module yet.B1.2, B2.2You will learn practical methods of reinforcement learning (RL) for sequential decision problems and how to apply them. In the end you will be able to model typical RL scenarios, implement common algorithms, and solve and assess simple robotics tasks (e.g. on the e-Puck) with RL.6 ECTSno date this semesterEI7641Artificial Intelligence in Medicine IINo ratings for this module yet.B1.2, B2.2You will gain an overview of advanced prediction and classification tasks in medicine. You will learn methods for prognosis and diagnostics (e.g., risk scores, survival models, differential diagnosis, population stratification), specialized ML techniques (geometric deep learning methods for point clouds/networks, transformers, reinforcement learning) as well as topics on trustworthiness and clinical implementation of AI (bias, fairness, generalizability, data harmonization, evaluation). By the end you can apply the concepts in your own AI projects and assess their social and ethical implications.5 ECTSno date this semesterIN2408Complexity TheoryNo ratings for this module yet.B1.2, B2.2You learn formal computational models (in particular Turing machines and circuits) as well as the most important complexity classes (e.g. L, NL, P, NP, PSPACE, EXP, NEXP, PH). By the end you will be able to analyze problems with respect to time and space complexity, apply reductions and completeness proofs, and classify advanced concepts such as alternation, randomized methods, and interactive proof systems.8 ECTSno date this semesterIN2007Compressed SensingNo ratings for this module yet.B1.2, B2.2You learn how to reconstruct sparse signals from a few structured linear measurements and which measurement matrices guarantee reliable recovery. In the end you can formulate important recovery statements, apply the Restricted Isometry Property (RIP) to random matrices, and use the underlying probabilistic proof techniques.5 ECTSno date this semesterMA5352Computational Inverse ProblemsNo ratings for this module yet.B1.2, B2.2You will learn mathematical and numerical methods for solving mainly linear inverse problems. In the end you will know the theory (ill-posedness, regularization, SVD, generalized Tikhonov) and common numerical procedures (direct and iterative regularization) as well as criteria for stability, convergence and stopping.6 ECTSno date this semesterMA4302Computational Social ChoiceNo ratings for this module yet.B1.2, B2.2You will become familiar with methods of collective decision making (Social Choice), with a focus on procedures that use majority relations and their algorithmic properties. In the end you will be able to analyze, compare, and assess the computational complexity of various election procedures.6 ECTSno date this semesterIN2229Computer Vision I: Variational MethodsNo ratings for this module yet.B1.2, B2.2You learn how many tasks of image processing (e.g. denoising, desmearing, segmentation, optical flow, stereo depth estimation, 3D reconstruction) are formulated and solved as variational problems. In the end you know the Euler–Lagrange approach and PDEs, efficient solution methods as well as convex formulations and relaxations and you can implement central concepts in Matlab.8 ECTSno date this semesterIN2246Computer Vision II: Multiple View Geometry (3D Computer Vision)No ratings for this module yet.B1.2, B2.2You will learn the mathematical foundations of multiple-view geometry in order to reconstruct camera motion and 3D geometry from several images. In the end you will understand image formation, epipolar geometry, camera calibration, rank conditions and bundle adjustment and you will be able to implement central algorithms in Matlab.8 ECTSno date this semesterIN2228FourieranalysisNo ratings for this module yet.B1.2, B2.2You learn the fundamentals of Fourier analysis on Euclidean spaces: Fourier series on period intervals and the Fourier transform on R^n, including generalizations to L^2 and distributions. In the end you will be able to assess convergence and regularity questions and apply Fourier techniques to applications such as PDEs, signal processing and sampling.5 ECTSno date this semesterMA4064Geometrie und Topologie für die DatenanalyseNo ratings for this module yet.B1.2, B2.2You will learn fundamental methods of geometric and topological data analysis. This includes constructions such as Voronoi and Delaunay diagrams, Alpha Shapes, as well as concepts from topology such as simplicial complexes and homology and their application to filtrations and persistent homology to investigate the topological properties of point sets.6 ECTSno date this semesterMA4804High-dimensional StatisticsNo ratings for this module yet.B1.2, B2.2You learn methods for the analysis of data where the number of variables is large. After the module you can apply procedures for controlling false discoveries in large-scale multiple testing, use sparse regression methods (e.g., Lasso) and methods for group-specific or low-dimensional structured signals, as well as use regularization approaches for matrix parameters and graph models.5 ECTSno date this semesterMA5442Introduction to Regularization and Learning Methods for Inverse ProblemsNo ratings for this module yet.B1.2, B2.2You will learn the mathematical foundations of inverse problems and regularization as well as modern data-driven solution approaches. In the end you will be able to analyze inverse problems, apply classical regularization methods and classify data-based reconstruction methods.5 ECTSno date this semesterCIT413070Machine Learning and IT-SecurityNo ratings for this module yet.B1.2, B2.2You will gain an overview of the intersection of Machine Learning and IT Security. You will learn how ML systems are used to detect attacks or spam/m malware, how ML systems themselves can be attacked and defended, and how audio deepfakes are produced and detected. In the end you will be able to design methods for anomaly detection, describe attacks on ML systems, and explain simple concepts of audio spoofing creation and detection.5 ECTSno date this semesterCIT4330001Machine Learning and OptimizationNo ratings for this module yet.B1.2, B2.2You will learn advanced concepts and methods of machine learning as well as common optimization procedures for their training. In the end you will be able to apply and further develop modern learning methods (e.g. deep neural networks), design optimization algorithms and analyze their behavior theoretically and empirically.5 ECTSno date this semesterEI70360Machine Learning for Regulatory GenomicsNo ratings for this module yet.B1.2, B2.2In this module you will learn biological fundamentals of gene regulation and modern deep learning methods for modeling sequence-based regulatory processes. After completion you will be able to apply genome-wide experimental procedures and deep learning models for different stages of gene expression and biologically interpret the model predictions.6 ECTSno date this semesterIN2393Manifold Optimization for Representation LearningNo ratings for this module yet.B1.2, B2.2In this module you will learn how to extract representations from data via optimization on matrix manifolds. In the end you will be able to describe central models of Representation Learning and derive and implement simple optimization algorithms on manifolds.6 ECTSno date this semesterEI71065Markov ProcessesNo ratings for this module yet.B1.2, B2.2You will learn theory and methods of continuous-time Markov processes: continuous-time Markov chains, the Markov property, Feller processes as well as properties of transition semigroups and their generators. In the end you can analyze the long-term behavior of processes, apply ergodic theorems and use them in examples (e.g. queueing theory, interacting particle systems, time series).9 ECTSno date this semesterMA4408Mathematical Foundations of ImagingNo ratings for this module yet.B1.2, B2.2You will learn mathematical foundations and models of imaging — from Fourier series and -transforms through frame theory and time-frequency analysis to wavelet transforms and variational methods. In the end you can compare different imaging models, apply their mathematical analysis, and employ suitable tools to solve concrete imaging problems.9 ECTSno date this semesterMA5063Mathematische Grundlagen der Neuronalen NetzeNo ratings for this module yet.B1.2, B2.2The module conveys selected mathematical foundations for the analysis of artificial neural networks. You will learn how approximation properties, stability with respect to input perturbations, and the learnability of networks are studied using various mathematical tools. In the end you will understand the central theoretical results and the analytical methods used.6 ECTSno date this semesterMA5913Numerical Methods for Uncertainty QuantificationNo ratings for this module yet.B1.2, B2.2You learn how to formulate, analyze, and numerically approximate elliptic boundary value problems with random coefficients. This includes modeling and sampling of random fields as well as numerical methods such as Monte Carlo, stochastic collocation, and stochastic Galerkin methods.6 ECTSno date this semesterMA5348Numerische Algorithmen für Computer Vision und Maschinelles LernenNo ratings for this module yet.B1.2, B2.2You learn numerical methods that are frequently used in computer vision and machine learning, including modeling of practical problems. In the end you will be able to implement basic algorithms, assess their strengths and weaknesses, and choose appropriate methods for solving concrete CV-/ML tasks.5 ECTSno date this semesterIN2384Online- und ApproximationsalgorithmenNo ratings for this module yet.B1.2, B2.2You will learn fundamentals and advanced techniques of online and approximation algorithms. In the end you will know classical online problems (e.g., scheduling, paging, k-server), analysis tools such as amortized analysis and randomized algorithms, as well as design techniques for approximation algorithms including LP-relaxation and randomized rounding.8 ECTSno date this semesterIN2304Optimale Steuerung gewöhnlicher Differentialgleichungen 1No ratings for this module yet.B1.2, B2.2You learn fundamental concepts and methods of optimal control for ordinary differential equations. In the end you will be able to formulate necessary optimality conditions (e.g., Euler–Lagrange, Legendre–Clebsch), distinguish different types of constraints and control restrictions, and convert control problems into boundary-value forms suitable for numerical treatment.5 ECTSno date this semesterMA3312Parallele AlgorithmenNo ratings for this module yet.B1.2, B2.2You deal with models of parallel computation and develop fundamental parallel algorithms. In the end you know various machine models, master basic knowledge of parallel complexity theory, and can design and evaluate parallel algorithms.8 ECTSno date this semesterIN2011Probability on GraphsNo ratings for this module yet.B1.2, B2.2You will learn stochastic models on graphs, e.g. Random Walks, percolation and random graphs. In the end you will be able to analyse Random Walks on networks, use the connection to electrical networks to show recurrence/transience, and understand phase transitions and random spanning trees.5 ECTSno date this semesterMA4406Quantitative VerificationNo ratings for this module yet.B1.2, B2.2You will learn how to formally model and analyze systems with quantitative aspects (e.g., time, probabilities). In the end you will be able to apply suitable model classes and specification languages, explain analysis algorithms and apply them to small examples practically, as well as use model checking tools.5 ECTSno date this semesterIN2340Randomisierte AlgorithmenNo ratings for this module yet.B1.2, B2.2You learn fundamentals and techniques of randomized algorithms and how to estimate their running time and correctness with probabilistic methods. In the end you will be able to understand and analyze classical randomized algorithms (e.g., randomized Quicksort, Min-Cut, Treaps) and apply tools such as Markov, Chebyshev and Chernoff inequalities.8 ECTSno date this semesterIN2160Solving Inverse Problems with Deep LearningNo ratings for this module yet.B1.2, B2.2You will learn modern, evidence-based methods for solving inverse problems in imaging and signal processing. In the end you will be able to apply deep-learning approaches for the reconstruction of signals/images, assess their foundations and limits, and design your own variants of existing methods.6 ECTSno date this semesterEI71068Statistical Inverse ProblemsNo ratings for this module yet.B1.2, B2.2You learn fundamental methods for the statistical treatment of inverse problems. The course covers linear inverse problems with random noise, regularization, convergence rates, adaptive procedures and model selection; at the end you can compare the results and apply them to concrete examples.5 ECTSno date this semesterMA5428Stochastic AnalysisNo ratings for this module yet.B1.2, B2.2You will learn the theory and fundamental applications of stochastic analysis. The focus is on Brownian motion (construction and properties), stochastic integrals and the Itô formula, as well as stochastic differential equations and methods such as Girsanov transformation and Donsker's invariance principle. In the end you will be able to formulate central statements and perform simple calculations with Itô integrals and SDEs.9 ECTSno date this semesterMA4405Tensor Network MethodsNo ratings for this module yet.B1.2, B2.2You learn modern methods for efficient approximation of high-dimensional functions (large N-tensors). The focus is on Tensor-Train (TT) approximation: its theory, numerical algorithms and applications. In the end you can analyze and simulate simple multidimensional problems with tensor-network methods.5 ECTSno date this semesterCIT413064Theorie der ZufallsmatrizenNo ratings for this module yet.B1.2, B2.2You learn non-asymptotic deviation estimates for random variables and vectors (in particular subgaussian and subexponential as well as isotropic vectors) and apply these concepts to random matrices with independent rows or columns. In the end you can formulate statements about the extreme singular values of such matrices, compare them and apply them to concrete examples as well as applications such as dimensionality reduction and Compressed Sensing.5 ECTSno date this semesterMA5346