AR-LIF: Adaptive reset leaky integrate-and-fire neuron for spiking neural networks
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909998471184384 |
|---|---|
| author | Huang, Zeyu Meng, Wei Liu, Quan Chen, Kun Ma, Li |
| author_facet | Huang, Zeyu Meng, Wei Liu, Quan Chen, Kun Ma, Li |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_20746 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AR-LIF: Adaptive reset leaky integrate-and-fire neuron for spiking neural networks Huang, Zeyu Meng, Wei Liu, Quan Chen, Kun Ma, Li Neural and Evolutionary Computing Artificial Intelligence Computer Vision and Pattern Recognition 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. |
| title | AR-LIF: Adaptive reset leaky integrate-and-fire neuron for spiking neural networks |
| topic | Neural and Evolutionary Computing Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.20746 |