Overview
Recent developments in neural networks (aka “deep learning”) have drastically advanced the performance of machine perception systems in a variety of areas including computer vision, robotics, and human shape modeling This course is a deep dive into deep learning algorithms and architectures with applications to a variety of perceptual and generative tasks.
Announcements
- 24.04.2024
- The mock exam is now available here.
- 05.02.2024
- Project descriptions have been added here!
- 03.01.2024
- More info coming soon!
Learning Objectives
Students will learn about fundamental aspects of modern deep learning approaches for perception and generation. Students will learn to implement, train and debug their own neural networks and gain a detailed understanding of cutting-edge research in learning-based computer vision, robotics, and shape modeling. The optional final project assignment will involve training a complex neural network architecture and applying it to a real-world dataset.
The core competency acquired through this course is a solid foundation in deep-learning algorithms to process and interpret human-centric signals. In particular, students should be able to develop systems that deal with the problem of recognizing people in images, detecting and describing body parts, inferring their spatial configuration, performing action/gesture recognition from still images or image sequences, also considering multi-modal data, among others.
We will focus on teaching: how to set up the problem of machine perception, the learning algorithms, network architectures, and advanced deep learning concepts in particular probabilistic deep learning models.
The course covers the following main areas:
I) Foundations of Deep Learning.
II) Advanced topics like probabilistic generative modeling of data (latent variable models, generative adversarial networks, auto-regressive models, invertible neural networks).
III) Deep learning in computer vision, human-computer interaction, and robotics.
Lecture Notes
You can download the lecture notes here (you will need to log in with your ETH LDAP).
These lecture notes are provided as a draft version for educational purposes only. The content presented herein is subject to change and may contain inaccuracies or errors. Grading for the course will be based on slides and the lecture materials.
Schedule
Subject to change. Materials only available from within ETH network.
| Wk. | Date | Content | Material | Exercise Session |
|---|---|---|---|---|
| 1 | 21.02 |
Deep Learning IntroductionClass content & admin |
slides |
|
| 1 | 22.02 |
-- No Class -- |
||
| 2 | 28.02 29.02 |
Training Neural NetworksBackpropagation |
slides pt. I slides pt. II Perceptron Visualization Notebook |
Tutorial Implement your own MLP slidesXOR Notebook XOR Solutions Eye-Gaze Notebook Eye-Gaze Solutions Tutorial Linear Regr. slidesLinear Regression Notebook Pen & Paper Backprop. exerciseexercise solution |
| 3 | 06.03. 07.03. |
Convolutional Neural Networks |
slides pt. I Additional material:
|
Tutorial CNNs in Pytorch slidesCNN Notebook Pen & Paper CNN exerciseexercise solution |
| 4 | 14.03. |
Recurrent Neural NetworksLSTM, GRU, Backpropagation through time |
slides |
Tutorial RNNs in Pytorch slidesRNN Notebook Pen & Paper RNN exerciseexercise solution |
| 5 | 20.03. 21.03 |
Generative Models Pt. I: Latent Variable ModelsVariational Autoencoders, etc. |
Class Tips for Training I slidesPen & Paper VAE exerciseexercise solution |
|
| 6 | 27.03. 28.03 |
Generative Models Pt. II: Autoregressive ModelsNade, Made, PixelCNN, PixelRNN, WaveNet |
Pen & Paper AR exerciseexercise solution |
|
| 7 | 03.04. 04.04. |
-- No Class or tutorials (Easter) -- |
||
| 8 | 10.04. 11.04. |
Generative Models Pt. III: Normalizing Flows and Invertible Neural Networks
|
Class Tips for Training II slidesPen & Paper NF exerciseexercise solution |
|
| 9 | 17.04. 18.04. |
Generative Models Pt. IV: Implicit ModelsGenerative Adversarial Networks & Co |
slides GAN Pt. I
slides GAN Pt. II |
Tutorial Exercise Discussion and Cluster slides Backprop&CNNslides cluster Pen & Paper GAN exerciseexercise solution |
| 10 | 24.04 25.04 |
Generative Models Pt. V: GAN Applications and Diffusion Models |
slides GAN Pt. III
slides Diffusion Models |
Tutorial RNN&VAE slides RNN&VAEPen & Paper class Diffusion Models exerciseexercise solution |
| 11 | 02.05. |
Reinforcement Learning |
slides RL pt. I |
Tutorial AR&NF slides AR&NFPen & Paper RL exerciseexercise solutions |
Exercise Sessions
Please refer to the above schedule once available for an overview of the planned exercise slots. We will have three different types of activities in the exercise sessions:
- Tutorial: Interactive programming tutorial in Python taught by a TA. Code will be made available.
- Class: Lecture-style class taught by a TA to give you some tips on how to train your neural network in practice.
- Pen & Paper: Pen & paper exercises that are not graded but are helpful to prepare for the written exam. Solutions will be published on the website a week after the release and discussed in the exercise session if desired.
Project
Overview
There will be a multi-week project that gives you the opportunity to have some hands-on experience with training a neural network for a concrete application.
The project grade will be determined by two factors: 1) a competitive part based on how well your model fairs compared to your fellow students' models and 2) the idea/novelty/innovativeness of your approach based on a written report to be handed in by the project deadline. For each project there will be baselines available that guarantee a certain grade for the competitive part if you surpass them. The competition will be hosted on an online platform.
Check out the project descriptions here (you will need to log in with your ETH LDAP).
Exam
To give you a rough idea what to expect for the exam, we release a mock exam which you can download here:
Cheatsheet policy in final exam: 2 double-sided sheets of A4 paper (4 sides in total) OR 4 sheets but written on 1 side (still 4 sides in total); Notes can be in digital (printed) or written form. It is not allowed to copy images or similar into digital notes and making digital notes excessively small; Font size of digital font should be no smaller than 11pt.
Registration as Non-primary Target Group
Registrations have been closed.