263-3710-00L  Machine Perception

Lehrveranstaltungen

Katalogdaten

Kurzbeschreibung	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.
Lernziel	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.
Inhalt	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, diffusion models). III) Deep learning in computer vision, human-computer interaction, and robotics. Specific topics include: I) Introduction to Deep Learning: a) Neural Networks and training (i.e., backpropagation) b) Feedforward Networks c) Timeseries modelling (RNN, GRU, LSTM) d) Convolutional Neural Networks II) Advanced topics: a) Latent variable models (VAEs) b) Generative adversarial networks (GANs) c) Autoregressive models (PixelCNN, PixelRNN, TCN, Transformer) d) Invertible Neural Networks / Normalizing Flows e) Coordinate-based networks (neural implicit surfaces, NeRF) f) Diffusion models III) Applications in machine perception and computer vision: a) Fully Convolutional architectures for dense per-pixel tasks (i.e., instance segmentation) b) Pose estimation and other tasks involving human activity c) Neural shape modeling (implicit surfaces, neural radiance fields) d) Deep Reinforcement Learning and Applications in Physics-Based Behavior Modeling
Literatur	Deep Learning Book by Ian Goodfellow and Yoshua Bengio
Voraussetzungen / Besonderes	This is an advanced grad-level course that requires a background in machine learning. Students are expected to have a solid mathematical foundation, in particular in linear algebra, multivariate calculus, and probability. The course will focus on state-of-the-art research in deep learning and will not repeat the basics of machine learning Please take note of the following conditions: 1) Students must have taken the exam in Machine Learning (252-0535-00) or have acquired equivalent knowledge 2) All practical exercises will require basic knowledge of Python and will use libraries such as Pytorch, scikit-learn, and scikit-image. We will provide introductions to Pytorch and other libraries that are needed but will not provide introductions to basic programming or Python. The following courses are strongly recommended as prerequisites: * "Visual Computing" or "Computer Vision" The course will be assessed by a final written examination in English. No course materials or electronic devices can be used during the examination. Note that the examination will be based on the contents of the lectures, the associated reading materials, and the exercises. The exam will be a 3-hour end-of-term exam and take place at the end of the teaching period.
Kompetenzen	Fachspezifische Kompetenzen Konzepte und Theorien geprüft Verfahren und Technologien geprüft Methodenspezifische Kompetenzen Analytische Kompetenzen geprüft Problemlösung geprüft Projektmanagement geprüft Soziale Kompetenzen Kommunikation gefördert Kooperation und Teamarbeit gefördert Menschenführung und Verantwortung gefördert Selbstdarstellung und soziale Einflussnahme gefördert Persönliche Kompetenzen Anpassung und Flexibilität gefördert Kreatives Denken gefördert Kritisches Denken gefördert Integrität und Arbeitsethik gefördert Selbststeuerung und Selbstmanagement gefördert

Leistungskontrolle

Information zur Leistungskontrolle (gültig bis die Lerneinheit neu gelesen wird)
Leistungskontrolle als Semesterkurs
ECTS Kreditpunkte	8 KP
Prüfende	O. Hilliges, J. Song
Form	Semesterendprüfung
Prüfungssprache	Englisch
Repetition	Die Leistungskontrolle wird nur am Semesterende nach der Lerneinheit angeboten. Die Repetition ist nur nach erneuter Belegung möglich.
Prüfungsmodus	schriftlich 180 Minuten
Zusatzinformation zum Prüfungsmodus	Optional project work during the semester will earn a bonus of up to 0.25 grade points on top of the final-exam grade. The maximum overall course grade of 6 cannot be exceeded, and can be achieved also without the project work.
Hilfsmittel schriftlich	limited aids (2 x A4 pages of hand written or digital notes with minimum 11pt font size)

Lernmaterialien

Gruppen

Einschränkungen

Angeboten in

Studiengang	Bereich	Typ
CAS in Informatik	Vertiefungsfächer und Wahlfächer	W
Cyber Security Master	Kernfächer	W
Cyber Security Master	Kernfächer	W
DAS in Data Science	Image Analysis & Computer Vision	W
DAS in Data Science	Machine Learning and Artificial Intelligence	W
Data Science Master	Wählbare Kernfächer	W
Elektrotechnik und Informationstechnologie Master	Vertiefungsfächer	W
Informatik Master	Kernfächer	W
Informatik Master	Kernfächer	W
Informatik Master	Ergänzung in Computer Vision	W
Informatik Master	Ergänzung in Machine Learning	W
Mathematik Master	Machine Learning	W
Robotics, Systems and Control Master	Kernfächer	W