[Comp-neuro] Code release: SpykeTorch
Timothee.MASQUELIER at cnrs.fr
Mon Jul 15 09:48:32 CEST 2019
We are proud to release our SpykeTorch open source code!
SpykeTorch is an efficient PyTorch-based simulator of convolutional spiking neural networks, in which the neurons emit at most one spike per stimulus, and use rank-order-coding.
It currently supports the STDP and Reward-modulated STDP learning rules.
It can reproduce various recent papers by us and others.
A Jupyter tutorial is provided, and an extensive documentation can be found here: http://cnrl.ut.ac.ir/SpykeTorch/doc/
See also the SpykeTorch paper: https://www.frontiersin.org/articles/10.3389/fnins.2019.00625/
Milad Mozafari, Mohammad Ganjtabesh, Abbas Nowzari-Dalini and Timothée Masquelier
More information about the Comp-neuro