Spiking Autoencoders With Temporal Coding

Abstract

Spiking neural networks with temporal coding schemes process information based on the relative timing of neuronal spikes. In supervised learning tasks, temporal coding allows learning through backpropagation with exact derivatives, and achieves accuracies on par with conventional artificial neural networks. Here we introduce spiking autoencoders with temporal coding and pulses, trained using backpropagation to store and reconstruct images with high fidelity from compact representations. We show that spiking autoencoders with a single layer are able to effectively represent and reconstruct images from the neuromorphically-encoded MNIST and FMNIST datasets. We explore the effect of different spike time target latencies, data noise levels and embedding sizes, as well as the classification performance from the embeddings. The spiking autoencoders achieve results similar to or better than conventional non-spiking autoencoders. We find that inhibition is essential in the functioning of the spiking autoencoders, particularly when the input needs to be memorised for a longer time before the expected output spike times. To reconstruct images with a high target latency, the network learns to accumulate negative evidence and to use the pulses as excitatory triggers for producing the output spikes at the required times. Our results highlight the potential of spiking autoencoders as building blocks for more complex biologically-inspired architectures. We also provide open-source code for the model.

VTSNN: a virtual temporal spiking neural network

“…Experimental results on a variety of datasets are often superior to the current SNN-based approach (Comşa et al, 2021 ) while superior to same-architecture ANN in some cases. In addition, VTSNN uses roughly 1/274 of the energy of ANN-based methods.…”

“…Therefore, we propose a novel symmetric and undistorted encoding-decoding method to fill the above gaps. Currently, researchers generally use STBP for the low-level SNN task (Comşa et al, 2021 ), which allows information to propagate in both temporal and spatial domains. Therefore, we present a new backpropagation that only permits information to propagate via the spatial domain.…”

“…This requirement substantially raises the bar for usage. Pioneers in this area introduced a novel SNN, requiring no specialized hardware (Comşa et al, 2021 ). Their performance, however, is not ideal, and our work will improve it.…”

“…But it is also distorted and requires a normalization trick. Comşa et al ( 2021 ) employed a latency coding method called time-to-first-spike (TTFS), inspired by biological vision (Hubel and Wiesel, 1962 ), to represent pixel brightness. TTFS cannot guarantee undistorted results, needs more time steps, and performs worse than ours.…”

Image sequence decomposition via sigma-delta cellular neural network having coupled cells

“…Neurons in the brain communicate and compute using discrete sparse signals called spikes. This mechanism is radically different from current mainstream artificial neural networks as known as deep neural networks [1][2][3]. Although deep neural networks are most potent in image processing tasks, it is said that their energy efficiency should be improved for edge computing [4].…”