A guide on how to implement Spiking Neural Networks in Tensorflow.
Tensorflow does not natively support SNNs, which means using core tf methods and API to implement them.
For the actual implementation, a Biophysical model (i.e., a Hodgkin-Huxley model) is used, based on: Izhikevich, Eugene M. Dynamical systems in neuroscience : the geometry of excitability and bursting. Cambridge, Mass. London: MIT Press, 2010, Chapter 8.
After cloning the repository, run
pip install -r requirements.txt
to install the dependencies.
Work is currently underway to demonstrate the application of an SNN to a classification task.