We develop neuro-inspired hardware platforms for real-time AI applications, deployed as SpiNNcloud at TUD Dresden University of Technology. We also work on the integration with other computing hardware, like other neuro-inspired hardware systems or FPGA, and focus on unsupervised learning of spiking neural networks.

Research Focus

• Development of the 2nd generation neuromorphic spinnaker system
• Energy-efficient real-time simulation of networks on the scale of the human brain
• Large-scale realisation of neuro-inspired AI algorithms
• Signal/image processing and machine learning for automotive and robotics applications
• Development of methods for artificial neural networks
• Development of machine learning methods in the field of cognitive data processing, including synaptic plasticity and dynamics in models for spiking neural networks (SNN)

Aims

Our long-term goal is to develop neuro-inspired models and learning algorithms for efficient execution on neuro-inspired hardware, supported by a simulation and model integration flow. These methods will
be developed for the SpiNNaker neuromorphic architecture, for FPGA platforms, as well as hybrid
architectures, providing a development and evaluation platform for novel computing architectures.