Introduction to Deep Learning (I2DL) (IN2346)

Welcome to the Introduction to Deep Learning course offered in WS26/27.

Announcements

• External student registration form is now available here.

General Course Structure

Lectures: In person, with recordings available on TUMLive.
Tutorials: Prerecorded, released every Thursday 10:00 a.m.
Exercises: Mostly coding, Jupyter-notebook and Python based, released every Thursday 10:00 a.m. Submissions are due the following Wednesday, 23:59.

The exercises will be used to determine a bonus for the exam. Please watch the first tutorial video at the beginning of the semester, where we will cover the class structure and planning in more detail. You will submit your solutions via our submission website. The exercise submissions will start in the first week of the semester. See below if you are an LMU or TUM student who currently can't sign up for the class via TUM Online.

External Students & Late TUM Online Registrations

We want to provide access to our lecture for as many students as possible. If you are affiliated with TUM (e.g. LMU student, Ph.D. student, TUM student who cannot register for courses yet but have a TUM token, etc.), we will add you to our class manually. To be added as an external student, please fill in the following form: External student registration form.

If you are a student from another university or simply interested in Deep Learning, you can access the lecture and exercise videos through this webpage, which will be updated accordingly. All notebooks feature separate tests where you can record your performance, though you will not be able to access the submission website. We will also provide solutions and discussions about the submissions in our weekly exercise videos, which are all publicly hosted on this website.

Lecture

Lecturer: Prof. Dr. Angela Dai

Time: Tuesdays, 14:00–16:00  ·  Lecture Hall: MI HS1  ·  ECTS: 6  ·  SWS: 4

Lecture Slides

• Lecture 1: Introduction to the lecture, Deep Learning, Machine Learning and submission
• Lecture 2: Machine Learning Basics
• Lecture 3: Introduction to Neural Networks
• Lecture 4: Optimization and Backprop
• Lecture 5: Scaling Optimization

Tutorials and Exercises

Tutorial and Exercise release date: Thursdays, 10:00

Exercise submission date: Wednesdays, 23:59

Lead Teaching Assistants: Chandan Yeshwanth, Haoxuan Li, Jiahui Fan

Tutorial Slides and Recordings

• Tutorial 1: Slides  ·  Recording
• Tutorial 2: Slides  ·  Recording
• Tutorial 3: Slides  ·  Recording
• Tutorial 4: Slides  ·  Recording

Exercises

• Exercise 1: Exercise  ·  Solution
• Exercise 2: Exercise  ·  Solution
• Exercise 3: Exercise  ·  Solution
• Exercise 4: Exercise

Office Hours

In addition to the tutorial we also offer to discuss questions in person. This semester, the office hours will be held via MS Teams. For each office hour, we provide a separate Teams link, see announcement on the forum. Please keep the following in mind to ensure the office hours remain helpful for everyone:

• Check out the correct Teams link for your time slot
• Mute your microphone when entering a Teams session
• Wait patiently until it's your turn; the TAs will answer questions in the order they are received (just as in the usual office hours).

Office hours start in the second week of the class. For one hour, you can speak directly with one of our TAs to resolve your questions. The links to these office hours can be accessed via the forum below and are only available to registered students.

Final Exam and Credits

The final exam will be on Monday, February 8, 2027, 17:00–18:30. The exam will be an onsite written exam, so please take this into consideration if you intend to receive credits for this class. Credits are only awarded for students that 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.

A mock exam and solution from a previous semester will be provided here for your reference during the semester.

Prerequisites

• Strong mathematical background: linear algebra, calculus.
• Previous knowledge of Python is needed. This includes scripting skills such as operating system calls.
• Machine Learning background is recommended.

Forum

We will use Moodle for discussions, publication of office hour links, and to distribute exam-related information. The slides and all other material will also be posted on Moodle, identical to what is hosted on this website.

TUM students enrolled in the course automatically have access to the Moodle course. External students (e.g. LMU students) will be added separately after filling in the external student registration form above.

Contact us

If you have any questions regarding the organization of the course, do not hesitate to contact us at i2dl@vc.in.tum.de. Please do not use the personal email addresses of the teaching assistants or tutors as these may go unanswered.

For questions on the syllabus, the exercises, or any other content of the lecture, please use the forum discussion board.

Course Recognition

For recognition of an equivalent course taken at a different university, please initiate contact through your study advisor and include all slides, exercises, syllabus, and other relevant information about the external course. Alternatively, you can send these directly to us on the course mailing list for assessment.