Machine Learning 2 – Master's Course

Technische Universität Berlin · Prof. Klaus-Robert Müller

This repository contains coursework from the graduate-level Machine Learning 2 course taught by Prof. Dr. Klaus-Robert Müller at Technische Universität Berlin during the Summer Semester 2022. The course is part of the Master’s in Computer Science program and explores how machines can learn from data — from statistical foundations to modern AI techniques.

Assignments include both analytical derivations and programming tasks.

---

Topics Covered

The course explored probabilistic approaches to learning, covering theory and practice of inference, generative modeling, and variational techniques:

1. Low-Dimensional Embedding – Locally Linear Embedding (LLE)
2. Component Analysis I – Canonical Correlation Analysis (CCA)
3. Component Analysis II – Independent Component Analysis (ICA)
4. Component Analysis III – Autoencoders
5. Kernel Machines I – Structured Kernels
6. Hidden Markov Models – Probabilistic sequence modeling
7. Kernel Machines II – Structured Prediction
8. Kernel Machines III – Anomaly Detection
9. Deep Learning I – Structured Networks
10. Deep Learning II – Structured Prediction
11. Deep Learning III – Explainable AI
12. Deep Learning IV – Anomaly Detection

---

Contents

The repository is organized into weekly folders (e.g., Week01, Week02, ...) following the course progression. Each folder typically contains:

• Analytical_Homework.pdf files with derivations and handwritten solutions
• Programming_Homework.ipynb notebooks implementing inference algorithms and generative models

This coursework is based on my own work, collaborative discussions within my homework group, and publicly provided materials. Redistribution or reuse of these materials for educational or institutional use is not permitted.

---

👉 Also see: Machine Learning 1 – Master's Course