The Institute for Machine Learning conducts research and provides profound education in machine learning. Its research focuses on development of machine learning and statistical methods. We further apply these methods to various domains like medicine, drug discovery, autonomous driving, earth science, natural language processing, control and others. The institute is led by Sepp Hochreiter and is affiliated with Johannes Kepler University Linz and is also one of the founding units of European Lab for Learning and Intelligent Systems (ELLIS).

The Institute for Machine Learning is located in the beautiful city of Linz, Austria. Located near the amazing Austrian alps, the once European capital of culture mixes the right balance between nature and urban life. A part of the institute is also located in the city of Vienna, Austria.

news

Sepp Hochreiter is on twitter now!
Paper accepted at ICLR 2021: Hopfield Networks is all you need
Talk by Sepp Hochreiter on the topic of Modern Hopfield networks and Dense associative memories: link
New blog post on the relationship of Performers and Hopfield Networks: link
New blog post on Cross domain few shot learning: link

recent publications

  1. ML4Molecules
    Task-conditioned modeling of drug-target interactions
    Svensson, E., Hoedt, P., Hochreiter, S., and Klambauer, G.
    In ELLIS Machine Learning for Molecule Discovery Workshop 2022
  2. FMDM
    Foundation Models for History Compression in Reinforcement Learning
    Paischer, F., Adler, T., Radler, A., Hofmarcher, M., and Hochreiter, S.
    2022
  3. AI4Science
    Robust task-specific adaption of models for drug-target interaction prediction
    Svensson, E., Hoedt, P., Hochreiter, S., and Klambauer, G.
    In NeurIPS 2022 AI for Science: Progress and Promises 2022
  4. CoLLAs
    Few-Shot Learning by Dimensionality Reduction in Gradient Space
    Gauch, M., Beck, M., Adler, T., Kotsur, D., Fiel, S., Eghbal-zadeh, H., Brandstetter, J., Kofler, J., Holzleitner, M., Zellinger, W., Klotz, D., Hochreiter, S., and Lehner, S.
    2022
  5. DeepRL
    InfODist: Online distillation with Informative rewards improves generalization in Curriculum Learning
    Siripurapu, R., Patil, V., Schweighofer, K., Dinu, M., Schmied, T., Diez, L., Holzleitner, M., Eghbal-zadeh, H., Kopp, M., and Hochreiter, S.
    2022
  6. ICML
    History Compression via Language Models in Reinforcement Learning
    Paischer, F., Adler, T., Patil, V., Bitto-Nemling, A., Holzleitner, M., Lehner, S., Eghbal-zadeh, H., and Hochreiter, S.
    In 2022
  7. JCIM
    Improving Few- and Zero-Shot Reaction Template Prediction Using Modern Hopfield Networks
    Seidl, P., Renz, P., Dyubankova, N., Neves, P., Verhoeven, J., Wegner, J., Segler, M., Hochreiter, S., and Klambauer, G.
    Journal of Chemical Information and Modeling 2022
  8. ICLR
    Normalization is dead, long live normalization!
    Hoedt, P., Hochreiter, S., and Klambauer, G.
    In ICLR Blog Track 2022
  9. CoLLAs
    A Dataset Perspective on Offline Reinforcement Learning
    Schweighofer, K., Radler, A., Dinu, M., Hofmarcher, M., Patil, V., Bitto-Nemling, A., Eghbal-zadeh, H., and Hochreiter, S.
    2022
  10. CoLLAs
    Reactive Exploration to Cope with Non-Stationarity in Lifelong Reinforcement Learning
    Steinparz, C., Schmied, T., Paischer, F., Dinu, M., Patil, V., Bitto-Nemling, A., Eghbal-zadeh, H., and Hochreiter, S.
    2022