Machine Learning & Data Analytics
How to use artificial intelligence and machine learning for data analysis.
Do you want to understand your data better? The Machine Learning & Data Analytics course helps you do that! The effective use of data science methods today requires an understanding of the basics of artificial intelligence and machine learning. Central to this is an understanding of the underlying algorithms, possibilities, limitations, and applications. Accordingly, the course conveys paradigms, concepts, principles, models, methods, and techniques for understanding and using artificial intelligence and machine learning for data analytics purposes. Various application examples will also be used to show how artificial intelligence and machine learning can be used in the real world.
Machine Learning and Data Analytics is really for everyone interested in the topic. The course is designed to start from scratch - no prior knowledge needed!
• Introduction to the basics of artificial intelligence and machine learning
• Description of typical problem types (e.g. regression, classification and dimension reduction)
• Theoretical description of common methods of machine learning, examples include linear and logistic regression,
support vector machines (SVMs), principal component analysis (PCA), and deep neural networks (DNN, deep
• Basics of Python programming in artificial intelligence and machine learning
• Practical application of machine learning methods to technical applications
• Understand models, methods, and concepts of artificial intelligence and machine learning
• Design, develop, and evaluate machine learning systems including (dis-)advantages
• Select promising machine learning methodologies for real-world use cases
• Have fun and delve deeper into data science!
• Interactive lectures
• Experiental exercises
• Hands-on programming experience
• Project-based group learning
• Plenary discussions
Basics of machine learning
• Introduction - motivation and terminology
• Application examples and potential
Introduction to tools
• Overview of existing software, tools and libraries
• Programming language: Python
Preprocessing and supervised learning
• Data preparation
• Feature selection and extraction
• Supervised learning methods: classification and regression
Supervised Learning: Deep Learning
• Artificial Neural Networks (ANN)
• Established deep learning architectures (e.g., Convolutional Neural Networks)
Evaluation and optimization
• Training, testing and validation
• (Hyper-)Parameter optimization
Prof. Dr. Björn Eskofier
Chair of Machine Learning & Data Analytics
Evening timetable: 6 days
At a glance
FAU certificate of participation
If you have any questions concerning the application process, please do not hesitate to contact our admissions office.