During my academic career, I’ve taught and mentored thousands of students in machine learning and related fields. I am passionate about breaking down complex concepts into clear, practical, and insightful materials that resonate with learners and professionals alike. I particularly enjoy crafting textbooks that offer accessible introductions to the core ideas of machine learning, bridging the gap between theory and application.
Published Books
Federated Learning: From Theory to Practice
Language: English
Publisher: Springer, 2026
ISBN: 978-981-95-1008-5 (Hardcover), 978-981-95-1011-5 (Softcover), 978-981-95-1009-2 (eBook)
The textbook Federated Learning: From Theory to Practice revolves around a flexible design principle for federated learning systems. This principle is referred to as generalized total variation minimization (GTVMin) serves as a natural analogue of empirical risk minimization (ERM), which underpins classical machine learning systems. The book develops federated learning methods systematically from this perspective and connects seamlessly to my earlier textbook, Machine Learning: The Basics.
Machine Learning: The Basics
Language: English
Publisher: Springer, 2022
ISBN: 978-981-16-8192-9 (Print), 978-981-16-8193-6 (eBook)
The textbook Machine Learning: The Basics offers a comprehensive introduction to the fundamental concepts of machine learning, covering key algorithms and techniques in an accessible way. This book is ideal for newcomers and those seeking to strengthen their understanding of core principles.
Maschinelles Lernen: Die Grundlagen
Language: German
Publisher: Springer, 2024
ISBN: 978-981-99-7971-4 (Print), 978-981-99-7972-1 (eBook)
“Maschinelles Lernen: Die Grundlagen” is the German translation of “Machine Learning: The Basics.” It brings the same clarity and foundational insights to German-speaking audiences, making it a valuable resource for students and professionals in machine learning.
Current Working Drafts
The Aalto Dictionary for Machine Learning
Language: English
Format: PDF
The Aalto Dictionary of Machine Learning is a curated, open-source glossary of essential terms and concepts in machine learning. Beyond serving as a concise reference for students and practitioners, the dictionary is published as a publicly available LaTeX codebase. You are explicitly encouraged to reuse its \TeX\ entries—with proper citation—for preparing lecture material, slides, and even scientific publications. This makes the dictionary not only a learning resource, but also a practical building block for teaching and communicating machine learning concepts with consistent notation and terminology.
Additional Resources
Stay tuned for updates on upcoming books and projects!