Featured books
We have developed two complimentary textbooks, the first one decomposes ML into three
main components: data, model, and loss function. The second book focuses on the
principles and practice of federated learning (FL), a paradigm for distributed machine learning with privacy
constraints. Both books are designed to be accessible and practical, with a focus on building intuition
and real-world applications.
Machine Learning: The Basics
Alexander Jung · Textbook
A concise, accessible introduction to modern ML concepts, methods, and intuition.
- Clear, compact coverage of supervised/unsupervised learning and evaluation.
- Builds intuition with minimal overhead; ideal as a first course companion.
- Widely used in teaching; pairs naturally with the Federated Learning textbook.
Federated Learning — From Theory to Practice
Alexander Jung · Textbook (forthcoming)
Unifying principles (incl. GTVMin), algorithms, systems, and real-world case studies.
- Bridges fundamentals to deployment: objectives, personalization, privacy, robustness.
- Hands-on: practical recipes, pitfalls, and design patterns for FL at scale.
- Applications: healthcare, sensors, and beyond; with exercises and figures.