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.

+More

technique stateoftheart hardware overhead sparse eventdriven computations cifar10 imagenet deep architecture spiking neural networks machine learning lowpower eventdriven neuromorphic hardware visual recognition problems vgg and residual network architectures snn

Abhronil Sengupta,Yuting Ye,Robert Wang,Chiao Liu,Kaushik Roy,.Going Deeper in Spiking Neural Networks: VGG and Residual Architectures. 13 (),.

Abhronil Sengupta,Yuting Ye,Robert Wang,Chiao Liu,Kaushik Roy,"Going Deeper in Spiking Neural Networks: VGG and Residual Architectures" 13

Abhronil Sengupta,Yuting Ye,Robert Wang,Chiao Liu,Kaushik Roy,"Going Deeper in Spiking Neural Networks: VGG and Residual Architectures"