Suchen Sie hier über ein Suchformular im Vorlesungsverzeichnis der Leuphana.

Veranstaltungen von Jennifer Matthiesen


Decomposing Neural Networks. An applicant's guide to artificial learning (Seminar)

Dozent/in: Jennifer Matthiesen, Tino Paulsen

14-täglich | Dienstag | 09:45 - 13:15 | 17.10.2022 - 03.02.2023 | HMS D19
Einzeltermin | Fr, 20.01.2023, 14:00 - Fr, 20.01.2023, 18:00 | C 12.002
Einzeltermin | Sa, 21.01.2023, 10:00 - Sa, 21.01.2023, 17:00 | C 12.002

Inhalt: Neural networks can generate artworks or beat the world champion in go by suggesting moves that no expert would consider. Metaphorical they are often described as black boxes, which are generally seen as uninterpretable by humans. But how black is the black box really? Why are those models so powerful? And where are their limits or weaknesses? Together we will look at the inner mechanism of neural networks, but likewise, dive into where the concepts are derived from. We will practically experiment with different architectures to deepen the understanding of the concepts, exploring their power but also their limitations.