Going Deeper in Spiking Neural Networks: VGG and Residual Architectures.

Over the past few years, Spiking Neural Networks (SNNs) have become popularas a possible pathway to enable low-power event-driven neuromorphic hardware.However, their application in machine learning have largely been limited tovery shallow neural network architectures for simple problems. In this paper,we propose a novel algorithmic technique for generating an SNN with a deeparchitecture, and demonstrate its effectiveness on complex visual recognitionproblems such as CIFAR-10 and ImageNet. Our technique applies to both VGG andResidual network architectures, with significantly better accuracy than thestate-of-the-art. Finally, we present analysis of the sparse event-drivencomputations to demonstrate reduced hardware overhead when operating in thespiking domain.