Spiking neural networks are networks that incorporate a time dimension into their process so that each neuron builds up energy and then releases distinct spikes. This process is very different from the typical one and leads to essentially a whole different sub field of machine learning that pursues this biologically inspired process. In this paper we have a review of many different frameworks for creating spiking neural networks. The coverage is broad and this document would provide a great first step for someone looking to implement a spiking neural network.
One great thing about many of the frameworks that have become available for pursuing new research in spiking neural networks is that they are built on top of existing frameworks like PyTorch and TensorFlow. This allows them to use GPU acceleration and a host of features that otherwise would likely be too maintenance intensive to be present in such frameworks. This also makes it easier for people with existing machine learning knowledge using common frameworks to experiment with spiking neural networks.