VVZ API is not affiliated with ETH Zurich. Data might be outdated or incorrect. Please view the official ETHZ Vorlesungsverzeichnis for binding information.
Abstract
Recent developments in neural networks 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.
Objective
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.
Content
The courses focuses on teaching how to set up the problem of machine perception and the associated learning algorithms, neural network architectures, and advanced deep learning concepts. The course covers the following main areas: I) Foundations of Deep Learning: Multilayer perceptrons, backpropagation, time-series modeling, convolutional neural networks. II) Advanced topics: latent variable models, generative adversarial networks, auto-regressive models, invertible neural networks, normalizing flows, diffusion models, neural implicit surface representations, neural radiance fields. III) Applications in machine perception and human-centric computer vision: general understanding of human activities, 3D reconstruction of human performance using different input modalities (monocular or multi-view images, body-worn sensors) and representations (explicit triangulated meshes, parametric body models, implicit surfaces, neural radiance fields, 3D Gaussian Splatting-based), Deep Reinforcement Learning and applications in physics-based behavior modeling.
Resources
Literature
Deep Learning Book by Ian Goodfellow, Yoshua Bengio, and Aaron Courville
Learning Materials (Links)
- Main link
- Information
General Information
- Language
- English
- Levels
- MSC , WBZ
- Frequency
- Yearly recurring
Examination
- Type
- end-of-semester examination
- Mode
- written 180 minutes
- Aids
- No electronic devices and calculators are allowed. A cheat sheet with the following restrictions is allowed: a maximum of 4 DIN A4 pages are allowed. They may be distributed over 2 double-sided sheets of paper or 4 sheets of paper written only on one side. Notes can be written digitally. It is not allowed to paste images or similar into the notes (both physical or digital) and making digital notes excessively small. If digital notes are typeset, the font size must be no smaller than 10 pt.
Registration & Places
- Max Places
- 300
Course Components
| Type | Title | Time & Place | Hours |
|---|---|---|---|
| lecture |
Machine Perception
Does not take place this semester.
|
No time listed | 3 h weekly |
| exercise |
Machine Perception
Does not take place this semester.
|
No time listed | 2 h weekly |
| independent project |
Machine Perception
Does not take place this semester.
|
No time listed | 2 h weekly |
Offered In
-
-
-
-
Application Area (Only necessary and eligible for the Master degree in Applied Mathematics. One of the application areas specified must be selected for the category Application Area for the Master degree in Applied Mathematics. At least 8 credits are required in the chosen application area. Credits from other application areas cannot be recognised for further application areas.)
-
-
-
-
Track: Signal Processing and Machine Learning (The core courses and specialization courses below are a selection for students who wish to specialize in the area of "Signal Processing and Machine Learning ", see . The individual study plan is subject to the tutor's approval.)
-
Specialization Courses (These specialization courses are particularly recommended for the area of "Signal Processing and Machine Learning", but you are free to choose courses from any other field in agreement with your tutor. Semester / Research Projects are not allowed in this category. A minimum of 40 credits must be obtained from specialization courses during the MSc EEIT.)
-
-
-
-
-
-
-
-
-
-
-
-
-
Deep Track Courses (At least 20 credits must be completed within the deep track courses. Surplus credit points can be counted towards the electives.)
-
-
Deep Track Robotics (These courses can be credited either as a specialization subject or as an elective subject.)
-
-
-