Lehrende: Prof. Dr. Christian Biemann; Dr. Timo Baumann
Veranstaltungsart: Seminar
Anzeige im Stundenplan: Deep Learning
Semesterwochenstunden: 2
Credits: 3,0
Unterrichtssprache: Deutsch / Englisch
Min. | Max. Teilnehmerzahl: - | 20
Kommentare/ Inhalte: Are you curious about machine learning, deep learning and language? In this seminar, we explore deep learning methods for language technology. We apply deep neural networks to selected machine learning problems in natural language processing (text) and speech processing (audio). Recent advancements in neural networks promise to learn data representations and relevant features from the data itself, as opposed to task-specific feature engineering. They have progressed the state-of-the-art in several language technology related tasks, in some cases significantly. The seminar includes hands-on sessions to learn relevant programming techniques, e.g. how to use and apply recurrent neural networks to sequential problems in Tensorflow, a mini-project and presentations of the results.
Lernziel: In this seminar, students learn - to apply deep neural networks to selected natural language processing problems - aspects of machine learning - aspects of neural networks - aspects of language technology - presentation techniques
Vorgehen: After a general introduction and a hands-on primer on programming deep neural networks in Python (e.g. with Tensorflow) in the first few sessions, we will distribute topics. The participants form teams to work on them and present their results in the seminar.
Literatur: individually assigned per topic
Zusätzliche Hinweise zu Prüfungen: To successfully pass, we ask the following: - mini-project: programming and training a deep learning model for a language technology task - seminar presentation of the results - small summary paper
