organisational stuff

• 30 min theory, 30 min Python notebook hacking
• first 3 or 4 weeks theory only

Outline of course

1. Introduction: What is Machine Learning?
2. Mathematical Background
3. Machine Learning Basics revisited
4. Python: Introduction to Python for Machine Learning
5. Regression
6. Classification
7. SVMs and Kernel methods
8. Decision Trees
9. Ensemble Learning (e.g. Random Forests)
10. Dimensionality Reduction
11. Clustering
12. Generative Models (e.g. Naive Bayes)
13. (Graphical Models)
14. Python: Introduction to Tensorflow / Keras
15. Neural networks
16. Deep learning

---

Literature

• [1] Pattern Recognition and Machine Learning - Bishop
• [2] Deep Learnig - Goodfellow, Bengio, Courville
• [3] Machine Learning: A Probabilistic Perspective - Murphy
• [4] The Elements of Statistical Learning - Hastie, Tibshirani, Friedman
• [5] (Artificial Intelligence: A modern approach - Russel, Norvig)
• [6] Introduction to Machine Learning - Alpaydin

---

interesting links:

The wonderful and terrifying implications of computers that can learn

Yann LeCun - Power & Limits of Deep Learning

Artificial Intelligence Augmentation