Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Sepp Hochreiter

Sepp Hochreiter

Few-Shot Learning by Dimensionality Reduction in Gradient Space

Jun 07, 2022
Martin Gauch, Maximilian Beck, Thomas Adler, Dmytro Kotsur, Stefan Fiel, Hamid Eghbal-zadeh, Johannes Brandstetter, Johannes Kofler, Markus Holzleitner, Werner Zellinger, Daniel Klotz, Sepp Hochreiter, Sebastian Lehner

Figure 1 for Few-Shot Learning by Dimensionality Reduction in Gradient Space

Figure 2 for Few-Shot Learning by Dimensionality Reduction in Gradient Space

Figure 3 for Few-Shot Learning by Dimensionality Reduction in Gradient Space

Figure 4 for Few-Shot Learning by Dimensionality Reduction in Gradient Space

* Accepted at Conference on Lifelong Learning Agents (CoLLAs) 2022. Code: https://github.com/ml-jku/subgd Blog post: https://ml-jku.github.io/subgd

Access Paper or Ask Questions

Entangled Residual Mappings

Jun 02, 2022
Mathias Lechner, Ramin Hasani, Zahra Babaiee, Radu Grosu, Daniela Rus, Thomas A. Henzinger, Sepp Hochreiter

Figure 1 for Entangled Residual Mappings

Figure 2 for Entangled Residual Mappings

Figure 3 for Entangled Residual Mappings

Figure 4 for Entangled Residual Mappings

* 21 Pages

Access Paper or Ask Questions

Hopular: Modern Hopfield Networks for Tabular Data

Jun 01, 2022
Bernhard Schäfl, Lukas Gruber, Angela Bitto-Nemling, Sepp Hochreiter

Figure 1 for Hopular: Modern Hopfield Networks for Tabular Data

Figure 2 for Hopular: Modern Hopfield Networks for Tabular Data

Figure 3 for Hopular: Modern Hopfield Networks for Tabular Data

Figure 4 for Hopular: Modern Hopfield Networks for Tabular Data

* 9 pages (+ appendix); 5 figures; source code available at: https://github.com/ml-jku/hopular ; blog post available at: https://ml-jku.github.io/hopular/

Access Paper or Ask Questions

Traffic4cast at NeurIPS 2021 -- Temporal and Spatial Few-Shot Transfer Learning in Gridded Geo-Spatial Processes

Apr 01, 2022
Christian Eichenberger, Moritz Neun, Henry Martin, Pedro Herruzo, Markus Spanring, Yichao Lu, Sungbin Choi, Vsevolod Konyakhin, Nina Lukashina, Aleksei Shpilman, Nina Wiedemann, Martin Raubal, Bo Wang, Hai L. Vu, Reza Mohajerpoor, Chen Cai, Inhi Kim, Luca Hermes, Andrew Melnik, Riza Velioglu, Markus Vieth, Malte Schilling, Alabi Bojesomo, Hasan Al Marzouqi, Panos Liatsis, Jay Santokhi, Dylan Hillier, Yiming Yang, Joned Sarwar, Anna Jordan, Emil Hewage, David Jonietz, Fei Tang, Aleksandra Gruca, Michael Kopp, David Kreil, Sepp Hochreiter

Figure 1 for Traffic4cast at NeurIPS 2021 -- Temporal and Spatial Few-Shot Transfer Learning in Gridded Geo-Spatial Processes

Figure 2 for Traffic4cast at NeurIPS 2021 -- Temporal and Spatial Few-Shot Transfer Learning in Gridded Geo-Spatial Processes

Figure 3 for Traffic4cast at NeurIPS 2021 -- Temporal and Spatial Few-Shot Transfer Learning in Gridded Geo-Spatial Processes

Figure 4 for Traffic4cast at NeurIPS 2021 -- Temporal and Spatial Few-Shot Transfer Learning in Gridded Geo-Spatial Processes

* Pre-print under review, submitted to Proceedings of Machine Learning Research

Access Paper or Ask Questions

CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP

Oct 21, 2021
Andreas Fürst, Elisabeth Rumetshofer, Viet Tran, Hubert Ramsauer, Fei Tang, Johannes Lehner, David Kreil, Michael Kopp, Günter Klambauer, Angela Bitto-Nemling, Sepp Hochreiter

Figure 1 for CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP

Figure 2 for CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP

Figure 3 for CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP

Figure 4 for CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP

* 14 pages (+ appendix); Blog: https://ml-jku.github.io/cloob GitHub: https://github.com/ml-jku/cloob

Access Paper or Ask Questions