Event-based neural network models such as biologically inspired spiking neural networks  have the ability to scale well  while being extremely energy efficient on neuromorphic hardware . While many efficient implementations exist [3,4], few support learning algorithms common in the deep learning community such as backpropagation.
Create a high-performance implementation of event-based models in an appropriate language such as Rust/Elixir or using CUDA. These implementations will also support standard learning algorithms from deep learning.
- Good Knowledge of Rust/Elixir/C++ and/or CUDA
- Knowledge of concurrent programming concepts
- Basic Knowledge in deep learning