Biologically-inspired training of spiking recurrent neural networks with neuromorphic hardware
- Thomas Bohnstingl
- Anja Surina
- et al.
- 2022
- AICAS 2022
Thomas Ortner (Bohnstingl) is with the group of Emerging computing and Circuits at IBM Research – Zurich. He holds a PhD degree in Computer Science under the supervision of Prof. Dr. Wolfgang Maass, as well as a separate Master’s degree in Technical Physics and Software Engineering and Management from Graz Technical University, Austria.
His current research focuses on network architectures for Foundation Models. This includes architectural research, associated learning theories and efficient implementation on cutting edge hardware accelerators. A specific focus is set on improving the capabilities and energy efficiency of state-of-the-art models with insights from neuroscience.
Neuro-inspired AI to optimize learning and computing efficiency of next generation AI.