Seminar: Deep Representation Learning - Details

Allgemeine Informationen

Veranstaltungsname	Seminar: Deep Representation Learning
Untertitel
Veranstaltungsnummer	8.3121
Semester	WiSe 2023/24
Aktuelle Anzahl der Teilnehmenden	48
Heimat-Einrichtung	LE Cognitive Science
Veranstaltungstyp	Seminar in der Kategorie Offizielle Lehrveranstaltungen
Erster Termin	Dienstag, 17.10.2023 10:00 - 12:00, Ort: 66/E01
Art/Form

Lehrende

• Ulf Krumnack, Ph.D.
• Lukas Niehaus
• Dr. Yusuf Brima

Räume und Zeiten

66/E01

Dienstag: 10:00 - 12:00, wöchentlich (13x)

Studienbereiche

• Veranstaltungen > Cognitive Science > Master-Programm
• Veranstaltungen > Cognitive Science > Bachelor-Programm

Modulzuordnungen

• Bachelor of Science Cognitive Science > CS-BW - Profilbildender Wahlbereich gültig ab WiSe 2019/20
• Bachelor of Science Informatik > CS-BWP-NI - Neuroinformatik gültig ab WiSe 2019/20
• Bachelor of Science Mathematik > CS-BWP-NI - Neuroinformatik gültig ab WiSe 2019/20
• Bachelor of Science Cognitive Science > CS-BWP-NI - Neuroinformatik gültig ab WiSe 2019/20
• Master of Science Mathematik > CS-BWP-NI - Neuroinformatik gültig ab WiSe 2019/20
• Master of Science Cognitive Science > CS-MW - Profilbildender Wahlbereich gültig ab WiSe 2019/20
• Master of Science Cognitive Science > CS-MWP-NI - Neuroinformatics

Kommentar/Beschreibung

The remarkable success of deep neural networks, as well as some of their fail-cases, are often attributed to the hierarchical and versatile representations they acquire during training. Despite the practical demonstration of their effectiveness, questions on: how to analyze, evaluate, and improve such representations are still the object of active research. In this seminar, we approach such questions, including a comparison of representations in different networks, methods for enforcing more "well-behaved," interpretable, and reusable representations, and learning representations for specific tasks vs. universal. The seminar will address these topics on a theoretical and practical level.

To fully benefit from this course, the ideal participant will have some background in deep learning, e.g., "ANNs with Tensorflow" course, and some experience with at least one of the current deep learning frameworks (e.g., TensorFlow or PyTorch). Additionally, a familiarity with some basic concepts in linear algebra, statistics, and information theory may be useful. By combining theoretical and practical approaches, this seminar aims to provide participants with a comprehensive understanding of the analysis, evaluation, and improvement of deep neural network representations.