Distributed Computing
ETH Zurich

Hands-On Deep Learning (FS 2023)

This lab introduces deep learning through the PyTorch framework in a series of hands-on exercises, exploring topics in computer vision, natural language processing, audio processing, graph neural networks, and representation learning.

In this lab, you will learn common as well as cutting-edge neural architectures. You will learn about various network structures as building blocks, and how to use them to solve introductory examples and course challenges. After attending this course, you will be familiar with multi-layer perceptrons, convolutional neural networks, recurrent neural networks, transformer encoders, graph convolutional/isomorphism/attention networks, and autoencoders.

Prerequisites This course has two prerequsites: (1) Students must have some familiarity with the ideas behind deep learning. Any course that teaches the fundamentals of deep learning, e.g. Computational Thinking (Chapters 5 and 6), is sufficient, and so is an adequate amount of self-study. (2) Students must know an imperative programming language, e.g., C, C++, Java, Javascript, or Python. The course uses Python as a programming language, so previous experience with Python is a plus (but not necessary). However, we expect students to either know or learn some of the basics of Python (e.g., lists, control structures, functions). Specifically, understanding the concepts of this Python Cheat Sheet is sufficient.

Sessions In each session, students work independently or in small groups, following a Python notebook, to explore various aspects of the topic of the given session. The step-by-step exercises are designed with intuition-building in mind. There are going to be TAs present at every session, answering students' questions and providing guidance where necessary.

Attendance Unexcused absences will result in a failing the lab. Excused absences are possible in case of illness or other emergencies. Contact the lab instructor in advance if you cannot attend a lab.

Time Wednesday 1st of March - 5th of April, 13:00-17:00

Place ETZ D96.1

Language English

Registration Link

Hardware Bring your preferred coding device. Some devices will also be available in the room.



Lab Date Material Colab TA Session TAs
Introduction to Deep Learning 1st of March Colab Notebook Peter Belcák Peter Belcák, Jonas Pai, Hyun-Min Chang
Perceptive Computer Vision 8th of March Colab Notebook Peter Belcák Peter Belcák, Jonas Pai, Hyun-Min Chang
Audio Processing 15th of March Colab Notebook Luca Lanzendörfer Luca Lanzendörfer, Jonas Pai, Hyun-Min Chang
Natural Language Processing 22nd of March Colab Notebook Florian Grötschla Florian Grötschla, Jonas Pai, Hyun-Min Chang
Generative Computer Vision 29th of March Colab Notebook Benjamin Estermann Benjamin Estermann, Jonas Pai, Hyun-Min Chang
Graph Neural Networks 5th of April Colab Notebook Joël Mathys Joël Mathys, Jonas Pai, Hyun-Min Chang