Going Deeper in Spiking Neural Networks: VGG and Residual Architectures
This enables low-power neuromorphic hardware to handle complex visual recognition tasks, advancing the field of event-driven AI.
The paper tackled the limitation of shallow Spiking Neural Networks (SNNs) by proposing a novel algorithmic technique to generate deep SNN architectures, achieving significantly better accuracy on CIFAR-10 and ImageNet than state-of-the-art methods.
Over the past few years, Spiking Neural Networks (SNNs) have become popular as a possible pathway to enable low-power event-driven neuromorphic hardware. However, their application in machine learning have largely been limited to very shallow neural network architectures for simple problems. In this paper, we propose a novel algorithmic technique for generating an SNN with a deep architecture, and demonstrate its effectiveness on complex visual recognition problems such as CIFAR-10 and ImageNet. Our technique applies to both VGG and Residual network architectures, with significantly better accuracy than the state-of-the-art. Finally, we present analysis of the sparse event-driven computations to demonstrate reduced hardware overhead when operating in the spiking domain.