PyGeNN documentation

GeNN is a software package to accelerate Spiking Neural Network simulations on hardware including NVIDIA GPUs using code generation. Networks are described using a simple Python API and the models and snippets used to describe the behaviour of the neurons and synapses which make up the networks are easily customised using strings containing a C-like language called GeNNCode.

Note, this documentation is under construction. If you cannot find what you are looking for, please contact the project developers.

• Installation
• Upgrading from GeNN 4
• Building networks
• Simulating networks
• Custom models
• Bibliography
• Tutorials
  • Defining populations of neurons
  • Adding synapses
  • Classification of a single digit
  • Classification of the entire test set
  • Faster classification of the whole test set
  • Presenting latency-coded inputs
  • Adding Kenyon Cells
  • Feedback-inhibition based gain control
  • Output neurons and learning
  • Testing
• User projects
• Reference documentation

GeNN is currently developed and maintained by

Dr James Knight (contact James)

Prof. Thomas Nowotny (contact Thomas)

The development of GeNN is partially supported by the EPSRC grant numbers:

• EP/V052241/1 - Unlocking spiking neural networks for machine learning research

• EP/P006094/1 - Brains on Board

• EP/J019690/1 - Green Brain Project.

Indices and tables

• Index

• Module Index

• Search Page