Vorlesung: 6061V Introduction to Deep Learning - Details

Vorlesung: 6061V Introduction to Deep Learning - Details

Sie sind nicht in Stud.IP angemeldet.

Allgemeine Informationen

Veranstaltungsname Vorlesung: 6061V Introduction to Deep Learning
Untertitel
Veranstaltungsnummer 6061V
Semester WiSe 21/22
Aktuelle Anzahl der Teilnehmenden 390
erwartete Teilnehmendenanzahl 100
Heimat-Einrichtung Professur für Angewandtes Maschinelles Lernen
Veranstaltungstyp Vorlesung in der Kategorie Lehre (mit Prüfung)
Erster Termin Dienstag, 19.10.2021 10:00 - 11:30 Uhr, Ort: (PHIL) HS 3
Art/Form
Qualifikationsziele
Kenntnisse / Skills/Knowledge:
Students will get to know about fundamentals of artificial neural networks, gain an overview on standard algorithms in the field as well as examples of recently proposed state-of-the-art techniques. Furthermore, students will get to know some standard tools to develop and apply deep learning techniques to machine learning problems.

Fähigkeiten / Abilities:
The students will be able to implement deep learning approaches to practical machine learning problems. They obtain the ability to choose and improve neural network architectures suitable for specific machine learning tasks.
Kompetenzen / Competencies: Students will strengthen their competence to analyze and assess algorithms for machine learning. Participants will learn to develop problem-oriented solutions with deep learning approaches independently.
Workload
60 contact hours + 120 h independent study and implementation
ECTS-Punkte
6

Räume und Zeiten

(PHIL) HS 1
Dienstag: 10:30 - 12:00, wöchentlich (14x)
Mittwoch, 06.04.2022 09:00 - 12:00
(PHIL) HS 3
Dienstag: 10:30 - 12:00, wöchentlich (1x)
(AM) HS 9
Mittwoch, 06.04.2022 09:00 - 12:00
(AM) HS 10
Mittwoch, 06.04.2022 10:00 - 12:00

Kommentar/Beschreibung

The course will give an overview on the fundamentals and current approaches for deep learning and its main applications fields. In particular, it will cover:
● Basics of Representation Learning
● Perceptron Learning
● Feedforward Neural Networks
● Gradient Descent and Backpropagation
● Regularization in Deep Learning
● Convolutional Neural Networks
● Recurrent Neural Networks
● Autoencoders
● Adversarial Training
● Graph Neural Networks
● Applications of Deep Learning for Text, Sequences, and Images
● Explainability and Deep Learning

Requirements: Advanced Topics in Data Science or Introduction to AI Engineering,
Python Programming Language

This lecture will be given in presence (offline).