Welcome to a comprehensive and freely accessible Introduction To Machine Learning. This course is meticulously designed to be self-contained, empowering you to learn at your own pace through a rich array of resources. We provide everything you need for effective self-study, including engaging lecture videos, detailed PDF slides, handy cheatsheets, interactive quizzes, practical exercises with complete solutions, and insightful notebooks.
Our extensive curriculum is thoughtfully structured into three progressive parts. The initial segment (Chapters 1-10) serves as an undergraduate-level introduction, building a strong foundational understanding. The second part (Chapters 11-19) advances to an MSc level, delving into more complex topics. Finally, the third course (Chapters 20-23), also at the MSc level, explores cutting-edge areas within machine learning. At the prestigious LMU Munich, these materials are utilized in an inverted-classroom setting for our B.Sc. lecture “Introduction to ML” and M.Sc. lectures “Supervised Learning” and “Advanced Machine Learning”. The initial part emphasizes building a practical and operational grasp of machine learning concepts, while the subsequent sections concentrate on the theoretical underpinnings and sophisticated algorithms that drive the field.
Deep Dive Sections: For those seeking a deeper theoretical understanding, certain sections offer exclusive mathematical proofs. These “deep-dive” sections are designed to provide rigorous insights into specific topics and are offered without accompanying videos to encourage focused study of the mathematical details.
Why Choose This Machine Learning Course? This course distinguishes itself by prioritizing the fundamental building blocks of machine learning. Rather than simply presenting a series of algorithms, we aim to cultivate a deeper understanding of the core principles that underpin the field. We thoroughly discuss, compare, and contrast key methodologies such as risk minimization, statistical parameter estimation, the Bayesian perspective, and information theory. We demonstrate how each of these serves as a valid and insightful entry point into machine learning. A primary objective is to develop your ability to navigate and switch between these diverse perspectives – a crucial skill often underemphasized in other introductory courses.
Furthermore, we are committed to making education truly open. This course is not only freely accessible but also open source, encouraging community contribution and further development.
Course Scope Limitations: Please note that this introduction to machine learning course does not include: (1) An exhaustive exploration of deep learning. For those interested in this area, we offer a dedicated course: Introduction to Deep Learning. (2) A comprehensive treatment of optimization. A separate course dedicated to optimization is currently under development to provide in-depth coverage of this crucial topic.
