AR-LIF: Adaptive reset leaky integrate-and-fire neuron for spiking neural networks
This work addresses a specific bottleneck in spiking neural networks for energy-efficient AI applications, though it appears incremental in nature.
The paper tackles the problem of information loss and uniform treatment in spiking neural networks by proposing an adaptive reset neuron with threshold adjustment, achieving state-of-the-art accuracy on Tiny-ImageNet and CIFAR10-DVS while maintaining low energy consumption.
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.