Spikingtorch documentation

About spikingtorch

spikingtorch is a package to train spiking neural networks in Pytorch using stochastic gradient descent methods.

Status

spikingtorch is still in development.

Quick install

The easiest way is directly through pypi:

pip install spikingtorch

Alternatively, you can directly obtain spikingtorch through its github repository.

Usage

Check the tutorial (Tutorial) for a brief introduction to spikingtorch.

Citing

If you want to acknowledge spikingtorch in a publication, you can cite the following work:

Coarse scale representation of spiking neural networks: backpropagation through spikes and application to neuromorphic hardware. This work is also available on arXiv.

Acknowledgements

  • Argonne National Laboratory’s Laboratory Directed Research and Development program.

  • Threadwork, U.S. Department of Energy Office of Science, Microelectronics Program. Website.

Contents