Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.17186 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918148625661952 |
|---|---|
| author | Zhang, Dehao Zhang, Malu Wang, Shuai Wang, Jingya Wei, Wenjie Ma, Zeyu Wang, Guoqing Yang, Yang Li, Haizhou |
| author_facet | Zhang, Dehao Zhang, Malu Wang, Shuai Wang, Jingya Wei, Wenjie Ma, Zeyu Wang, Guoqing Yang, Yang Li, Haizhou |
| contents | The explosive growth in sequence length has intensified the demand for effective and efficient long sequence modeling. Benefiting from intrinsic oscillatory membrane dynamics, Resonate-and-Fire (RF) neurons can efficiently extract frequency components from input signals and encode them into spatiotemporal spike trains, making them well-suited for long sequence modeling. However, RF neurons exhibit limited effective memory capacity and a trade-off between energy efficiency and training speed on complex temporal tasks. Inspired by the dendritic structure of biological neurons, we propose a Dendritic Resonate-and-Fire (D-RF) model, which explicitly incorporates a multi-dendritic and soma architecture. Each dendritic branch encodes specific frequency bands by utilizing the intrinsic oscillatory dynamics of RF neurons, thereby collectively achieving comprehensive frequency representation. Furthermore, we introduce an adaptive threshold mechanism into the soma structure that adjusts the threshold based on historical spiking activity, reducing redundant spikes while maintaining training efficiency in long sequence tasks. Extensive experiments demonstrate that our method maintains competitive accuracy while substantially ensuring sparse spikes without compromising computational efficiency during training. These results underscore its potential as an effective and efficient solution for long sequence modeling on edge platforms. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_17186 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Dendritic Resonate-and-Fire Neuron for Effective and Efficient Long Sequence Modeling Zhang, Dehao Zhang, Malu Wang, Shuai Wang, Jingya Wei, Wenjie Ma, Zeyu Wang, Guoqing Yang, Yang Li, Haizhou Machine Learning Artificial Intelligence The explosive growth in sequence length has intensified the demand for effective and efficient long sequence modeling. Benefiting from intrinsic oscillatory membrane dynamics, Resonate-and-Fire (RF) neurons can efficiently extract frequency components from input signals and encode them into spatiotemporal spike trains, making them well-suited for long sequence modeling. However, RF neurons exhibit limited effective memory capacity and a trade-off between energy efficiency and training speed on complex temporal tasks. Inspired by the dendritic structure of biological neurons, we propose a Dendritic Resonate-and-Fire (D-RF) model, which explicitly incorporates a multi-dendritic and soma architecture. Each dendritic branch encodes specific frequency bands by utilizing the intrinsic oscillatory dynamics of RF neurons, thereby collectively achieving comprehensive frequency representation. Furthermore, we introduce an adaptive threshold mechanism into the soma structure that adjusts the threshold based on historical spiking activity, reducing redundant spikes while maintaining training efficiency in long sequence tasks. Extensive experiments demonstrate that our method maintains competitive accuracy while substantially ensuring sparse spikes without compromising computational efficiency during training. These results underscore its potential as an effective and efficient solution for long sequence modeling on edge platforms. |
| title | Dendritic Resonate-and-Fire Neuron for Effective and Efficient Long Sequence Modeling |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2509.17186 |