Projects per year
Organisation profile
Organisation profile
The Institute for Machine Learning conducts internationally renowned research and provides profound education in machine learning. Its research focuses on development and application of machine learning and statistical methods.
Fields of science
- 101031 Approximation theory
- 102 Computer Sciences
- 305901 Computer-aided diagnosis and therapy
- 102033 Data mining
- 101029 Mathematical statistics
- 102032 Computational intelligence
- 101028 Mathematical modelling
- 102013 Human-computer interaction
- 305905 Medical informatics
- 101027 Dynamical systems
- 101004 Biomathematics
- 101026 Time series analysis
- 101024 Probability theory
- 202017 Embedded systems
- 102019 Machine learning
- 202037 Signal processing
- 305907 Medical statistics
- 102018 Artificial neural networks
- 103029 Statistical physics
- 202036 Sensor systems
- 202035 Robotics
- 106005 Bioinformatics
- 106007 Biostatistics
- 101019 Stochastics
- 101018 Statistics
- 101017 Game theory
- 101016 Optimisation
- 102001 Artificial intelligence
- 101015 Operations research
- 102004 Bioinformatics
- 101014 Numerical mathematics
- 102003 Image processing
JKU Focus areas
- Digital Transformation
-
Zertifizierung von Deep Learning (TÜV III)
Hochreiter, S. (PI)
01.03.2025 → 28.02.2027
Project: Contract research › Industry project
-
Cluster of Excellence "Bilateral Artificial Intelligence"
Fürnkranz, J. (PI), Hochreiter, S. (PI), Klambauer, G. (PI), Schedl, M. (PI), Seidl, M. (PI) & Widmer, G. (PI)
01.10.2024 → 30.09.2029
Project: Funded research › FWF - Austrian Science Fund
-
AlKa-DL: Alpine karst spring discharge prediction
Brandstetter, J. (PI)
01.10.2024 → 30.09.2027
Project: Funded research › FWF - Austrian Science Fund
Research output
-
5D Neural Surrogates for Nonlinear Gyrokinetic Simulations of Plasma Turbulence
Galletti, G., Paischer, F., Setinek, P., Hornsby, W., Zanisi, L., Carey, N., Pamela, S. & Brandstetter, J., 11 Feb 2025.Research output: Working paper and reports › Preprint
-
Data efficiency and long-term prediction capabilities for neural operator surrogate models of edge plasma simulations
Carey, N., Zanisi, L., Pamela, S., Gopakumar, V., Omotani, J., Buchanan, J., Brandstetter, J., Paischer, F., Galletti, G. & Setinek, P., 24 Feb 2025.Research output: Working paper and reports › Preprint
-
DEALing with Image Reconstruction: Deep Attentive Least Squares
Pourya, M., Kobler, E., Unser, M. & Neumayer, S., 06 Feb 2025.Research output: Working paper and reports › Preprint
Open Access
Activities
-
A New Generation of Foundation Models Based on xLSTM
Klambauer, G. (Keynote speaker)
19 May 2025Activity: Talk or presentation › Invited talk › science-to-science
-
Shape Generation via Weight Space Learning
Plattner, M. (Speaker)
27 Apr 2025Activity: Talk or presentation › Poster presentation › science-to-science
-
xLSTM: The Comeback Story of LSTM
Hochreiter, S. (Speaker)
24 Apr 2025Activity: Talk or presentation › Other talk or presentation › science-to-public
Prizes
-
-
-
Director of the ELLIS Machine Learning for Molecules Discovery research program
Klambauer, G. (Recipient), 2023
Prize: Other distinction