Advanced Deep Learning (ADL)5 ECTS
(englische Bezeichnung: Advanced Deep Learning)

Lehrveranstaltungen:

• • Advanced Deep Learning
    (Vorlesung mit Übung, Katharina Breininger et al., Zeit und Raum n.V.)

Empfohlene Voraussetzungen:

We strongly recommend students to have acquired a thorough understanding of fundamental Deep Learning techniques, e.g., from the lecture + exercises "Deep Learning".

Inhalt:

Deep Learning-based algorithms showed great performance in many fields of image processing and pattern recognition and compete with technologies such as compressive sensing and iterative optimization. The basis for the success of these algorithms is the availability of large amounts of data (big data) for training and of high computing power (typically GPUs).
In this course we will explore advanced deep learning methods. In particular, we will aim to develop a deeper understanding of topics beyond SGD optimization, CNNs and simple RNN networks, for example: graph neural networks, unsupervised learning, differentiable learning, invertible learning, neural ordinary differential equations, transfer learning, multi-task learning, uncertainty DL. Additionally, we will develop both a sound theoretical understanding of these approaches and identify areas of application for these advanced techniques.

Lernziele und Kompetenzen:

By the end of this course, students will be able to:

• understand advanced techniques in deep learning

• identify a suitable approach as well as its benefits and shortcomings

• choose/design and conduct a small research project

• read a recent paper in the discipline and design a follow-up experiment

Studien-/Prüfungsleistungen:

Advanced Deep Learning (Prüfungsnummer: 651933)

(englischer Titel: Advanced Deep Learning)

mündliche Prüfung, Dauer (in Minuten): 30, benotet

weitere Erläuterungen:
The oral exam will include questions on lectures, exercises and class projects.

Erstablegung: SS 2023, 1. Wdh.: WS 2023/2024

1. Prüfer:

Katharina Breininger