Lectures Syllabus 2026
| Date | Lecture | Teacher | Materials | Reading |
| 18.02.2026 | 1. Recap of Machine Learning, Multi-Layer Perceptron | AS | slides | Goodefellow 5.2-5.5 |
| 25.02.2026 | 2. Backpropagation | AS | | |
| 04.03.2026 | 3. History + CNN + DeepSet | AS | | |
| 11.03.2026 | 4. Training Deep Models (Init, Norm, etc.) | AS | | |
| 18.03.2026 | 5. Regularization Methods for NNs | AS | | |
| 25.03.2026 | 6. Stochastic Gradient Descent (SGD) | AS | | |
| 01.04.2026 | 7. Self-Attention, Transformers | GT | | |
| 08.04.2026 | 8. Adaptive Optimization Methods | AS | | |
| 15.04.2026 | 9. Learning Representations I: Word Vectors, Metric Learning | AS | | |
| 22.04.2026 | 10. Adversarial Patterns, Biases, Security | GT | | |
| 29.04.2026 | 11. Graph Neural Networks | GT | | |
| 06.05.2026 | 12. Learning Representations II: VAE (+ diffusion) | AS | | |
| 13.05.2026 | — Rector's day — | | | |
| 20.05.2026 | 13. TBA (tentatively Autoregressive, SSM) | AS | | |