Exploiting High Performance Spiking Neural Networks with Efficient Spiking Patterns

TL;DR

This paper introduces a novel neuron model inspired by biological spike patterns, enhancing the performance and efficiency of Spiking Neural Networks on various datasets, including static and neuromorphic data.

Contribution

The paper proposes the LIFB neuron with adaptive burst patterns and a decoupling method for efficient hardware implementation, improving SNN performance and latency.

Findings

Improved accuracy on CIFAR10, CIFAR100, and ImageNet datasets.

Achieved state-of-the-art results on neuromorphic datasets DVS-CIFAR10 and NCALTECH101.

Significantly reduced network latency while maintaining high performance.

Abstract

Spiking Neural Networks (SNNs) use discrete spike sequences to transmit information, which significantly mimics the information transmission of the brain. Although this binarized form of representation dramatically enhances the energy efficiency and robustness of SNNs, it also leaves a large gap between the performance of SNNs and Artificial Neural Networks based on real values. There are many different spike patterns in the brain, and the dynamic synergy of these spike patterns greatly enriches the representation capability. Inspired by spike patterns in biological neurons, this paper introduces the dynamic Burst pattern and designs the Leaky Integrate and Fire or Burst (LIFB) neuron that can make a trade-off between short-time performance and dynamic temporal performance from the perspective of network information capacity. LIFB neuron exhibits three modes, resting, Regular spike, and Burst spike. The burst density of the neuron can be adaptively adjusted, which significantly enriches the characterization capability. We also propose a decoupling method that can losslessly decouple LIFB neurons into equivalent LIF neurons, which demonstrates that LIFB neurons can be efficiently implemented on neuromorphic hardware. We conducted experiments on the static datasets CIFAR10, CIFAR100, and ImageNet, which showed that we greatly improved the performance of the SNNs while significantly reducing the network latency. We also conducted experiments on neuromorphic datasets DVS-CIFAR10 and NCALTECH101 and showed that we achieved state-of-the-art with a small network structure.