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.
|Hopfield Networks is all you needPaper accepted at ICLR 2021:|
|linkTalk by Sepp Hochreiter on the topic of Modern Hopfield networks and Dense associative memories:|
|linkNew blog post on the relationship of Performers and Hopfield Networks:|
|linkNew blog post on Cross domain few shot learning:|
|spotlight presentation at NeurIPS 2020: Modern Hopfield Networks and Attention for Immune Repertoire ClassificationPaper accepted with|
- arXivMC-LSTM: Mass-Conserving LSTM2021
- ICLRHopfield Networks Is All You Need2020
- arXivCross-Domain Few-Shot Learning by Representation FusionarXiv preprint arXiv:2010.06498 2020
- arXivConvergence Proof for Actor-Critic Methods Applied to PPO and RUDDER2020
- arXivAlign-RUDDER: Learning From Few Demonstrations by Reward RedistributionarXiv preprint arXiv:2009.14108 2020
- NeurIPSModern Hopfield networks and attention for immune repertoire classificationIn Advances in Neural Information Processing Systems 2020
- arXivLarge-Scale Ligand-Based Virtual Screening for SARS-CoV-2 Inhibitors Using Deep Neural Networks2020
- On Failure Modes in Molecule Generation and Optimization2020