Spiking Neural Network Dataset

The dataset used in this paper is a spiking neural network (SNN) with 20 layers, where each layer has 2000 LIF neurons. The input spikes are Poisson trains at a target rate of 10Hz, and the output spikes are Poisson trains at a target rate of 30Hz. The network is trained using surrogate gradient descent with a piecewise-constant surrogate function.