The Institute of Theoretical Computer Science is looking for an outstanding and highly motivated
PhD Student or Postdoc
to complement our team in the Faculty of Computer Science and Biomedical Engineering of Graz University of Technology .
The researcher will work on advancing Deep Learning and methods for understanding its outcomes ("interpretable AI") for applications to large data-based cortical microcircuit models, using state-of-the-art supercomputing facilities. The goals are to elucidate the organization of computing and learning in neural networks of the brain, and to develop on this basis spike-based AI methods. The research will be based on recently developed algorithms and TensorFlow software for spiking neural networks, as published for example in
- G. Bellec, D. Salaj, A. Subramoney, R. Legenstein, and W. Maass. Long short-term memory and learning-to-learn in networks of spiking neurons. 32nd Conference on Neural Information Processing Systems (NIPS 2018), https://igi-web.tugraz.at/PDF/243.pdf
- G. Bellec, F. Scherr, A. Subramoney, E. Hajek, D. Salaj, R. Legenstein, and W. Maass. A solution to the learning dilemma for recurrent networks of spiking neurons. Nature Communications, 2020. https://www.nature.com/articles/s41467-020-17236-y.pdf
- F. Scherr, C. Stoeckl, and W. Maass. One-shot learning with spiking neural networks. bioRxiv, 2020. https://igi-web.tugraz.at/PDF/256.pdf
This is a fully funded research position in the Human Brain Project of the EU, which offers an exciting international interdisciplinary research environment.
Requirements
- Strong mathematical background and analytical skills
- Deep interest in understanding the function of neural networks in the brain
- Excellent programming skills
- Very good knowledge in Machine Learning
Contact
Please send your CV, grades, motivation letter, and links to pdf of your master thesis and other relevant preceding work to
charlotte.rumpf@tugraz.at
