AR-LIF: Adaptive reset leaky integrate-and-fire neuron for spiking neural networks

TL;DR

This paper introduces AR-LIF, an adaptive reset neuron for spiking neural networks that improves accuracy and energy efficiency by dynamically adjusting thresholds and reset modes, achieving state-of-the-art results on benchmark datasets.

Contribution

The paper proposes a novel adaptive reset mechanism for spiking neurons that enhances performance and energy efficiency over traditional reset methods.

Findings

Achieves state-of-the-art accuracy on Tiny-ImageNet and CIFAR10-DVS datasets.

Maintains lower energy consumption compared to existing models.

Demonstrates the effectiveness of adaptive reset in SNNs.

Abstract

Spiking neural networks offer low energy consumption due to their event-driven nature. Beyond binary spike outputs, their intrinsic floating-point dynamics merit greater attention. Neuronal threshold levels and reset modes critically determine spike count and timing. Hard reset cause information loss, while soft reset apply uniform treatment to neurons. To address these issues, we design an adaptive reset neuron that establishes relationships between inputs, outputs, and reset, while integrating a simple yet effective threshold adjustment strategy. Experimental results demonstrate that our method achieves excellent performance while maintaining lower energy consumption. In particular, it attains state-of-the-art accuracy on Tiny-ImageNet and CIFAR10-DVS. Codes are available at https://github.com/2ephyrus/AR-LIF.