Skip to main content
x

Benchmarking modern SNN training algorithms on GeNN

Tags:
Status:
Completed
Contributor/Mentors

Manvi Agarwal 
Jamie Knight 
Thomas Nowotny

About

GeNN is a GPU-enhanced Neuronal Network simulation package in C++, that combines the ease of code generation, primarily for the purpose of setting up the parameters of the simulation through a model definition, with the flexibility of user-defined code, to actually run the simulation and record results. While there are several SNN libraries available, by combining GeNN and standard machine learning packages, it is possible to simulate SNNs and ANNs on the same hardware, thereby providing well-founded comparisons of model performance. This project will primarily use Python (PyGeNN, TensorFlow, Jupyter for tutorials), along with C++ (GeNN).

Deliverables
  • Combine GeNN and other machine learning packages using Python (PyGeNN, TensorFlow, Jupyter for tutorials) and C++ (GeNN)
  • Provide easier code generation and code flexibility 
  • Compare the performance of different models