Applied artificial intelligence

Credit transfer modules: Mathematics & Statistics, Methodological Skills, Personal and Social Skills in the Workplace, Programming I, Programming II

Machine Learning Algorithms

The module provides fundamentals and methods of machine learning. Topics include supervised, unsupervised, and reinforcement learning, model evaluation, and data preparation. In addition, algorithms such as random forest, SVM, and regression, as well as clustering and dimensionality reduction, are covered to develop and analyze data-driven models.

Advanced Mathematics and Statistics

The module provides advanced knowledge in mathematics and statistics. Topics include linear algebra, multidimensional optimization, and fundamentals of analysis. In addition, advanced statistical methods such as conditional probabilities, regression techniques, and Bayesian models are covered to analyze complex data and mathematical models.

Programming with AI Frameworks

The module provides fundamentals of programming with AI frameworks. Topics include Python, development and execution models, and efficient data processing through vectorization, parallelization, and GPU acceleration. In addition, scientific libraries such as NumPy and pandas as well as deep learning frameworks like PyTorch and TensorFlow are covered.

Neural Networks

The module provides fundamentals of neural networks and deep learning. Topics include different network types such as FFN, CNN, RNN, and LSTM, as well as training methods using gradient descent and backpropagation. In addition, optimization techniques, normalization, regularization, and hyperparameter tuning are covered to develop effective AI models.

Data Handling & Technologies

The module provides fundamentals of data management and modern data processing technologies. Topics include relational and non-relational databases, SQL, and distributed processing with Hadoop and Spark. In addition, data preparation, visualization, and MLOps are covered to efficiently develop data-driven applications.

Applied Scientific Research

The module provides fundamentals of academic writing and good scientific practice. Topics include the structure, development, and evaluation of academic papers, literature research, and formal writing style. In addition, research management, presentation techniques, review processes, and practical applications in AI are covered.

Deep learning for computer vision

The module provides fundamentals and applications of deep learning for computer vision. Topics include image representation, classical image processing, and modern methods such as convolutional neural networks for classification, object detection, and segmentation. In addition, model training, evaluation, generative models, and frameworks like PyTorch and Keras are covered.

Deep learning for speech and text understanding

The module provides fundamentals of deep learning for language and text understanding. Topics include text and audio processing, language models, and neural networks. In addition, applications such as NLP, translation, speech recognition, speech synthesis, and chatbots are covered. Practical exercises deepen the application of methods.

Project

The module enables independent work on practical projects in collaboration with industry or research groups. Students plan, organize, and manage the project within a team. Topics include analysis, implementation, and documentation of results. The project concludes with a presentation, a written report, and submission of the developed code.

Master's Thesis

The master’s thesis involves the independent scientific analysis of a problem from industry or research. It includes literature and patent research, development and implementation of a solution concept, and critical evaluation of results. The work is documented in writing and presented and defended in a final colloquium.

Credit transfer modules: Mathematics & Statistics, Methodological Skills, Personal and Social Skills in the Workplace, Programming I, Programming II

Machine Learning Algorithms

The module provides fundamentals and methods of machine learning. Topics include supervised, unsupervised, and reinforcement learning, model evaluation, and data preparation. In addition, algorithms such as random forest, SVM, and regression, as well as clustering and dimensionality reduction, are covered to develop and analyze data-driven models.

Advanced Mathematics and Statistics

The module provides advanced knowledge in mathematics and statistics. Topics include linear algebra, multidimensional optimization, and fundamentals of analysis. In addition, advanced statistical methods such as conditional probabilities, regression techniques, and Bayesian models are covered to analyze complex data and mathematical models.

Programming with AI Frameworks

The module provides fundamentals of programming with AI frameworks. Topics include Python, development and execution models, and efficient data processing through vectorization, parallelization, and GPU acceleration. In addition, scientific libraries such as NumPy and pandas as well as deep learning frameworks like PyTorch and TensorFlow are covered.

Neural Networks

The module provides fundamentals of neural networks and deep learning. Topics include different network types such as FFN, CNN, RNN, and LSTM, as well as training methods using gradient descent and backpropagation. In addition, optimization techniques, normalization, regularization, and hyperparameter tuning are covered to develop effective AI models.

Data Handling & Technologies

The module provides fundamentals of data management and modern data processing technologies. Topics include relational and non-relational databases, SQL, and distributed processing with Hadoop and Spark. In addition, data preparation, visualization, and MLOps are covered to efficiently develop data-driven applications.

Applied Scientific Research

The module provides fundamentals of academic writing and good scientific practice. Topics include the structure, development, and evaluation of academic papers, literature research, and formal writing style. In addition, research management, presentation techniques, review processes, and practical applications in AI are covered.

Deep learning for computer vision

The module provides fundamentals and applications of deep learning for computer vision. Topics include image representation, classical image processing, and modern methods such as convolutional neural networks for classification, object detection, and segmentation. In addition, model training, evaluation, generative models, and frameworks like PyTorch and Keras are covered.

Deep learning for speech and text understanding

The module provides fundamentals of deep learning for language and text understanding. Topics include text and audio processing, language models, and neural networks. In addition, applications such as NLP, translation, speech recognition, speech synthesis, and chatbots are covered. Practical exercises deepen the application of methods.

Project

The module enables independent work on practical projects in collaboration with industry or research groups. Students plan, organize, and manage the project within a team. Topics include analysis, implementation, and documentation of results. The project concludes with a presentation, a written report, and submission of the developed code.

Master's Thesis

The master’s thesis involves the independent scientific analysis of a problem from industry or research. It includes literature and patent research, development and implementation of a solution concept, and critical evaluation of results. The work is documented in writing and presented and defended in a final colloquium.