Modules

17 results

B Elective Modules17

B1.1, B2.1, B317

B1.1 Data Analysis17

Discrete OptimizationNo ratings for this module yet.B1.1, B2.1, B3 › B1.1 Data AnalysisYou will learn central concepts and algorithms of linear integer optimization and combinatorial optimization. In the module you will analyze mathematical structures that allow efficient solution methods, and you will be able to model real problems as discrete optimization problems and identify special cases that are efficiently solvable.9 ECTSruns this semesterCIT413041Functional AnalysisNo ratings for this module yet.B1.1, B2.1, B3 › B1.1 Data AnalysisYou will learn the basics of functional analysis in Banach and Hilbert spaces. In the end you will be able to analyze linear functionals and bounded as well as compact self-adjoint operators, understand duality, and apply concepts such as weak and weak* convergence.9 ECTSruns this semesterMA3001Fundamentals of Mathematical StatisticsNo ratings for this module yet.B1.1, B2.1, B3 › B1.1 Data AnalysisYou will learn the fundamental principles and methods of statistical inference, including likelihood approaches, Bayesian methods and minimax estimation. You will deal with asymptotic theory for large samples and apply it in particular to the study and application of maximum-likelihood techniques.9 ECTSruns this semesterMA5441Nonlinear OptimizationNo ratings for this module yet.B1.1, B2.1, B3 › B1.1 Data AnalysisYou engage with theory and numerical methods of nonlinear optimization. You will learn advanced methods for unconstrained and, in particular, constrained optimization problems (e.g., SQP, barrier and interior-point methods) and you will be able to assess and apply convergence properties of such methods in the end.5 ECTSruns this semesterMA3503Probability TheoryNo ratings for this module yet.B1.1, B2.1, B3 › B1.1 Data AnalysisYou will learn the measure-theoretic probability theory for sequences of random variables and martingales. By the end you will be able to understand and apply central results such as the law of large numbers, central limit theorems, and fundamental martingale results.9 ECTSruns this semesterMA2409
12 more in B1.1 Data AnalysisStatistical Foundations of LearningNo ratings for this module yet.B1.1, B2.1, B3 › B1.1 Data AnalysisYou learn statistical foundations of machine learning theory and mathematical tools for the analysis of learning algorithms. In the end you will be able to evaluate generalization and consistency questions, theoretically analyze algorithms such as k‑NN, SVM and simple neural networks, and contextualize newer developments such as overparameterization and training dynamics.8 ECTSruns this semesterCIT4230004Approximation AlgorithmsNo ratings for this module yet.B1.1, B2.1, B3 › B1.1 Data AnalysisYou learn how to design and analyze efficient approximation algorithms for combinatorial optimization problems. In the end you can assess the running time and approximation guarantees of algorithms, apply known techniques (e.g. Greedy, LP-Rounding, Primal-Dual), and prove limits of approximability.9 ECTSno date this semesterCIT4100003CausalityNo ratings for this module yet.B1.1, B2.1, B3 › B1.1 Data AnalysisYou engage with concepts and methods of causal inference: from probabilistic and graph-theoretic foundations through structural models to modern algorithms for causal discovery and estimation of causal effects. In the end you can judge whether and how causal conclusions are possible from given data and assumptions, select appropriate methods and apply them in practice.8 ECTSno date this semesterIN2410Fundamentals of Optimization for Machine LearningNo ratings for this module yet.B1.1, B2.1, B3 › B1.1 Data AnalysisYou will learn fundamentals and advanced techniques of optimization, both convex and nonconvex as well as combinatorial and continuous, with a focus on applications in machine learning. In the end you will be able to understand optimization problems from ML research and approach research questions in this area.5 ECTSno date this semesterCIT413031Generalized Linear ModelsNo ratings for this module yet.B1.1, B2.1, B3 › B1.1 Data AnalysisYou learn methods of regression for non-normally distributed target variables (e.g., binary, count data, nominal, positive values). In addition to classical GLMs such as logistic, Probit-, Poisson-, Gamma-, and log-linear models, extensions (e.g., overdispersion, random effects) are covered. By the end you will be able to estimate models, validate them, and analyze and interpret the results with R.9 ECTSno date this semesterMA3403Graphical Models in StatisticsNo ratings for this module yet.B1.1, B2.1, B3 › B1.1 Data AnalysisIn this module you will learn multivariate statistical models whose joint distributions are described by graphs. In the end you will be able to identify dependency and conditional-independence structures, design suitable graphical models for datasets, and analyze the models practically with R.9 ECTSno date this semesterMA5439Mathematical Data AnalysisNo ratings for this module yet.B1.1, B2.1, B3 › B1.1 Data AnalysisYou will learn methods for analyzing complex and unstructured data, including regression and classification tasks. The module provides fundamentals such as loss functions, positive definite kernels and reproducing kernel Hilbert spaces as well as regularization strategies (e.g. Tikhonov) and SVM regression. In addition, summation procedures and manifold learning are covered.6 ECTSno date this semesterMA5098Mathematical Foundations of Machine LearningNo ratings for this module yet.B1.1, B2.1, B3 › B1.1 Data AnalysisYou will learn the mathematical foundations of modern machine learning methods: structure, learning algorithms and approximation properties of neural networks, theory and application of kernel methods in reproducing kernel Hilbert spaces as well as qualitative aspects such as loss functions, risk and complexity questions. By the end you will be able to construct networks, discuss their approximation properties, apply kernel methods and assess the statistical efficiency of procedures.6 ECTSno date this semesterMA4801Mathematical Foundations of Machine LearningNo ratings for this module yet.B1.1, B2.1, B3 › B1.1 Data AnalysisYou will learn the mathematical foundations of modern methods of machine learning. By the end you can design neural networks and discuss their approximation properties, apply kernel methods in Reproducing Kernel Hilbert Spaces, and assess the statistical efficiency of learning procedures.9 ECTSno date this semesterCIT413048Modern Methods in Nonlinear OptimizationNo ratings for this module yet.B1.1, B2.1, B3 › B1.1 Data AnalysisYou will learn selected modern methods of nonlinear optimization, e.g. convex and non-smooth optimization, interior-point methods, semidefinite programming, robustness concepts and duality. In the end you will be able to understand current research articles on the treated topics and you will be prepared to pursue your own research questions in nonlinear optimization.5 ECTSno date this semesterMA4503Polyhedral CombinatoricsNo ratings for this module yet.B1.1, B2.1, B3 › B1.1 Data AnalysisYou learn how to approach combinatorial optimization problems through the geometry of polyhedra: representation of polytopes, the connection between geometry and optimization of linear functions, as well as modern algorithms such as branch-and-cut and separation/optimization. In the end you will be able to apply the methods to typical problems (e.g., matching, TSP polytopes) and assess their limits in the context of NP-hardness.6 ECTSno date this semesterMA5225TopologyNo ratings for this module yet.B1.1, B2.1, B3 › B1.1 Data AnalysisYou learn the fundamentals of set-theoretic topology and algebraic topology. In the first part you analyze topological and metric spaces as well as concepts such as continuity, compactness and connectedness; in the second part you deal with homotopies, fundamental groups and singular homology. At the end of the module you can assess topological properties as well as determine fundamental groups and homology of simple spaces.9 ECTSno date this semesterMA3241