Sepp Hochreiter
Corresponding Member of the Division of Mathematics and Natural Sciences in Austria since 2024
- Johannes Kepler Universität Linz
Contact:
Orcid-ID:
0000-0001-7449-2528
Research Areas:
- Computer Sciences
- Artificial intelligence
- Machine learning
- Artificial neural networks
- Bioinformatics
Profile:
Publications:
Selected Memberships:
- European Lab for Learning and Intelligent Systems
- Association for Computing Machinery (ACM)
- Österreichische Computer Gesellschaft (OCG)
Selected Prizes:
- 2020: IEEE Neural Networks Pioneer Award (highest award in Deep Learning)
- 2023: German KI-lnnovation Award of the "Welt"
- 2022: Austrian Innovation Award
- 2022: Digitalos (Digital Pioneer Award)
- 2019: Upper Austrian of the year: category economic and science
Selected Publications:
- Hochreiter, S., & Schmidhuber, J. (1997). Long shortterm memory. Neural computation, 9, 1735-1780.
- Heusel, M., Ramsauer, H., Unterthlner, T., Nessler, B., &Hochreiter, S. (2017). GANs trained by a two time-scale update rule converge to a local Nash equilibrium. Advances in Neural Information Processing Systems, 30.
- Clevert, O.-A., Unterthiner, T, & Hochreiter, S. (2016). Fast and Accurate Deep Net-work Learning by Exponential Linear Units (ELUs). 4th International Conference on Leaming Representations.
- Klambauer, G., Unterthiner, T., Mayr, A., & Hochreiter, S. (2017). Self-normalizing neural nehvorks. Advances in Neural Information Processing Systems, 31, 972-981.
- Hochreiter, S. (1998). The vanishing gradient problem during leaming recurrent neural nets and problem solutions. Internat. J. Uncertain. Fuzziness Knowledge- Based Sys-tems, 6, 107-116.