Spiking-GAN: A Spiking Generative Adversarial Network Using Time-To-First-Spike Coding

Abstract

Spiking Neural Networks (SNNs) have shown great potential in solving deep learning problems in an energy-efficient manner. However, they are still limited to simple classification tasks. In this paper, we propose Spiking-GAN, the first spike-based Generative Adversarial Network (GAN). It employs a kind of temporal coding scheme called time-tofirst-spike coding. We train it using approximate backpropagation in the temporal domain. We use simple integrate-and-fire (IF) neurons with very high refractory period for our network which ensures a maximum of one spike per neuron. This makes the model much sparser than a spike rate-based system. Our modified temporal loss function called 'Aggressive TTFS' improves the inference time of the network by over 33% and reduces the number of spikes in the network by more than 11% compared to previous works. Our experiments show that on training the network on the MNIST dataset using this approach, we can generate high quality samples. Thereby demonstrating the potential of this framework for solving such problems in the spiking domain.

Fully Spiking Variational Autoencoder

“…Spiking GAN (Kotariya and Ganguly 2021) uses two-layer SNNs to construct a generator and discriminator to train a GAN; however, the quality of the generated image is low. One reason for this is that the time-to-first spike encoding cannot grasp the entire image in the middle of spike trains.…”

“…In particular, image generation models based on SNNs have not been studied sufficiently. Spiking GAN (Kotariya and Ganguly 2021) built a generator and discriminator with shallow SNNs, and generated images of handwritten digits by adversarial learning. However, its generation quality was low, and some undesired images were generated that could not be interpreted as numbers.…”