Login
Introduction to Deep Learning (IN2346)
Welcome to the Introduction to Deep Learning course offered in WS24/25.
Course Structure
| What | When | Where | Who |
|---|---|---|---|
| Lecture | Tuesdays, 14:00-16:00 | MI HS 1 | Prof. Dr. Daniel Cremers |
| Tutorial&Exercise | Thursdays, 10:00-12:00 | Online | TA Team |
Lectures: Live streamed and recorded automatically via TUM-Live: https://live.rbg.tum.de/
Tutorials: Pre-recorded, uploaded every Thursday, 10:00 AM.
Exercises: Mostly coding, jupyter-notebooks and Python based, uploaded every Thursday, 10:00 AM.
Period: 15.10.2024 - 06.02.2025
Language: English
ECTS: 6
SWS: 4
Prerequisites
- Strong mathematical background: linear algebra, calculus.
- Previous knowledge of Python, including scripting skills such as operating system calls.
- Machine Learning background.
Registration
If you plan to attend, please register for the course on TUMonline. Later during the semester, you will have to register for the exam.
For students who cannot register via TUMonline, please fill in this form: https://forms.gle/x2gR9hXayAhiLFJ5A.
Anouncements and Discussions
We use Piazza instead of Moodle. Please join the class via the link: https://piazza.com/tum.de/fall2024/in2346ws2425.
Lectures
| Date | Slides | Recording |
|---|---|---|
| 15.10 | Lecture 01: Introduction | Lecture 01 |
| 22.10 | Lecture 02: Machine Learning Basics | Lecture 02 |
| 29.10 | Lecture 03: Introduction to Neural Networks | Lecture 03 |
| 05.11 | Lecture 04: Optimization and Backpropagation | Lecture 04 |
| 12.11 | Lecture 05: Scaling Optimization | Lecture 05 |
| 19.11 | Lecture 06: Training Neural Networks | Lecture 06 |
| 26.11 | Lecture 07: Loss Functions and Activations | Lecture 07 |
| 03.12 | Lecture 08: Augmentation and Regularization | Lecture 08 |
| 10.12 | Lecture 09: Convolutional Neural Networks | Lecture 09 |
| 17.12 | Lecture 10: CNN Architectures | Lecture 10 |
| 07.01 | Lecture 11: RNNs and Transformers | Lecture 11 |
| 14.01 | Guest Lecture | |
| 21.01 | Lecture 12: Advanced Deep Learning Topics | Lecture 12 (Part 1) |
| 28.01 | Research Projects in Computer Vision Group | |
| 04.02 | Lecture 12 (Part 2) |
Tutorials and exercises
| Date | Slides | Video | Exercise |
|---|---|---|---|
| 17.10 | Tutorial 01: Organization | Tutorial 01 | Exercise 01 |
| 24.10 | Tutorial 02: Math Recap | Tutorial 02 | Exercise 02 (solution) |
| 31.10 | Tutorial 03: Data | Tutorial 03 | Exercise 03 (solution) |
| 07.11 | Tutorial 04: Simple Classifier | Tutorial 04 | Exercise 04 (solution) |
| 14.11 | Tutorial 05: Neural Networks | Tutorial 05 | Exercise 05 (solution) |
| 21.11 | Tutorial 06: Hyperparameter Tuning | Tutorial 06 | Exercise 06 (solution) |
| 28.11 | Tutorial 07: PyTorch | Tutorial 07 | Exercise 07 (solution) |
| 05.12 | Tutorial 08: Autoencoder | Tutorial 08 | Exercise 08 (solution) |
| 12.12 | Tutorial 09: Convolutional Neural Nnetworks | Tutorial 09 | Exercise 09 (solution) |
| 09.01 | Tutorial 10: Semantic Segmentation | Tutorial 10 | Exercise 10 (solution) |
| 16.01 | Tutorial 11: NLP | Tutorial 11 | Exercise 11 (solution) |
| 23.01 | Included in Tutorial 11 | Exercise 12 |
Final Exam and Credits
The final exam will be on 12 Feb 2025, 16:30 - 18:00. The exam will most likely be a traditional onsite exam, so please take this into consideration if you intend to receive credits for this class. Credits are only awarded to students who participated and successfully passed the exam.
As this course is taught every semester, there will be no retake exam; you will have to take next semester's exam (bonus will be transferred).
We provide a mock exam and the solution for your reference.
Contact
Please refrain from sending us emails individually. You can contact us for individual regards through the email: i2dl@vision.in.tum.de. All TAs of the course will receive these emails.
