Course Material

1. PyTorch Introduction (05.04.2022): Slides
2. Tensors (12.04.2022): Presentation, exercise 1, exercise 1 solution
3. Data Encoding and Embeddings (19.04.2022): Presentation, exercise 2
4. Python Refresher (26.04.2022): Exercise, exercise solutions
5. Data Encoding and Embeddings (continued) (03.05.2022)
6. Building Neural Models (10.05.2022): Presentation, exercise 3
7. Linear regression with PyTorch (17.05.2022): Exercise 4
8. Linear regression with PyTorch (continued) (24.05.2022)
9. Training by gradient descent (31.05.2022): Presentation, exercise 5, exercise 4 solution
10. Training by gradient descent (continued) (07.06.2022)
11. Pretrained Embeddings (14.06.2022): Exercise 6
12. Training and Evaluation (21.06.2022): Exercise 7
13. RNN’s/LSTMs (28.06.2022): Exercise 8
14. RNN’s/LSTMS (05.07.2022): Exercise 8 (2.0), Project Guidelines

Practical Homework

1. Homework 1 (Deadline: 17.05.2022), Solution
2. Homework 2 (Deadline: 25.05.2022), Solution
3. Homework 3 (Deadline: 08.06.2022), Solution
4. Homework 4 (Exercise 3 of the practical session) (Deadline: 22.06.2022)
5. Homework 5 (Exercise 1 of the practical session) (Deadline: 30.06.2022)
6. Homework 6 (Exercise 8 (2.0)) (Deadline: 15.07.2022)

Theoretical Homework

1. Homework 1 (Deadline: 09.05.2022)
2. Homework 2 (Deadline: 13.06.2022)
3. Homework 3 (Deadline: 04.07.2022)