Go to JKU Homepage
Institute for Machine Learning
What's that?

Institutes, schools, other departments, and programs create their own web content and menus.

To help you better navigate the site, see here where you are at the moment.

Deutsch, Sprache wechseln
Go to JKU Homepage

Dipl.-Ing. Pieter-Jan Hoedt

Research Topics

  • Deep Learning and Neural Networks

  • Initialisation and Normalisation

  • Signal Propagations

Selected Publications:

- Normalization is dead, long live Normalization! (2022), opens an external URL in a new window, Pieter-Jan Hoedt, Sepp Hochreiter, Günter Klambauer. ICLR Blog Track (https://iclr-blog-track.github.io/2022/03/25/unnormalized-resnets/, opens an external URL in a new window ) [PDF, opens a file]

- MC-LSTM: Mass Conserving LSTM (2021), opens an external URL in a new window, Pieter-Jan Hoedt, Frederik Kratzert, Daniel Klotz, Christina Halmich, Markus Holzleitner, Grey S Nearing, Sepp Hochreiter, Günter Klambauer. Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4275-4286 [PDF, opens a file]

 

Go to JKU Homepage

Johannes Kepler University Linz

Altenberger Straße 69

4040 Linz, Austria

Telephone +43 732 2468 0
Fax +43 732 2468 4929
Contact