Two types of labs (tutorials) will be proposed for the course (alternating):
Date | Topic | Teachers | Assignment | Notes |
---|---|---|---|---|
17.02.2022 | Lab 1: Preparations, Double Descent | AS | rec 102 rec 103 | |
24.02.2022 | Seminar 1 (lecture 1) | BF | assignments | rec 102 rec 103 |
03.03.2022 | Lab 2: Backpropagation, Computational graph | AS | rec 102 rec 103 | |
10.03.2022 | Seminar 2 (lectures 2,3) | BF | assignments | rec 103 |
17.03.2022 | Lab 3: Pytorch, project pipeline, CNN, performance metrics | AS | rec 102 rec 103 | |
24.03.2022 | Seminar 3 (lectures 4,5) | AS | assignments | rec 103 |
31.03.2022 | Lab 4: Pre-trained CNN Fine-tuning with regularization, BN | AS | rec 102 | |
07.04.2022 | Seminar 4 (lectures 6,7) | BF | assignments | rec 102 |
14.04.2022 | Lab 5: CNN visualization & adversarial patterns | BF | rec 102 | |
21.04.2022 | Seminar 5 (lectures 8,9) | AS | assignments | rec 102 |
28.04.2022 | Lab 6: Metric learning | AS | rec 102 | |
05.05.2022 | Seminar 6 (lectures 10,11) | AS | assignments | no record |
12.05.2022 | Lab 7: VAE | BF | rec 102 | |
19.05.2022 | Seminar 7 (lecture 12) | BF | assignments | no record |
The seminar assignments are published 1 week in advance before the seminar. You are expected to prepare for it at home. We discuss the problems and solutions in the class. You are not required to submit you solutions, but if you solved a problem you will be invited to present it in the class. Seminars are not scored by points but they are important for gaining technical understanding, which will be finally evaluated in the written exam.
Examples of problems with solutions: examples.pdf (to be updated)
The solutions of the practical labs have to be submitted using the upload system
You may choose from the following submission variants:
Please do not submit data and any other redundant files. Sharing code that is not a required part of the assignment is permitted, for example additional visualization code or test cases for debugging.