General Self-Prediction Enhancement for Spiking Neurons
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914291316162560 |
|---|---|
| author | Huang, Zihan Xu, Zijie Huang, Yihan Jia, Shanshan Bu, Tong Dong, Yiting Liu, Wenxuan Ding, Jianhao Yu, Zhaofei Huang, Tiejun |
| author_facet | Huang, Zihan Xu, Zijie Huang, Yihan Jia, Shanshan Bu, Tong Dong, Yiting Liu, Wenxuan Ding, Jianhao Yu, Zhaofei Huang, Tiejun |
| contents | Spiking Neural Networks (SNNs) are highly energy-efficient due to event-driven, sparse computation, but their training is challenged by spike non-differentiability and trade-offs among performance, efficiency, and biological plausibility. Crucially, mainstream SNNs ignore predictive coding, a core cortical mechanism where the brain predicts inputs and encodes errors for efficient perception. Inspired by this, we propose a self-prediction enhanced spiking neuron method that generates an internal prediction current from its input-output history to modulate membrane potential. This design offers dual advantages, it creates a continuous gradient path that alleviates vanishing gradients and boosts training stability and accuracy, while also aligning with biological principles, which resembles distal dendritic modulation and error-driven synaptic plasticity. Experiments show consistent performance gains across diverse architectures, neuron types, time steps, and tasks demonstrating broad applicability for enhancing SNNs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_21823 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | General Self-Prediction Enhancement for Spiking Neurons Huang, Zihan Xu, Zijie Huang, Yihan Jia, Shanshan Bu, Tong Dong, Yiting Liu, Wenxuan Ding, Jianhao Yu, Zhaofei Huang, Tiejun Neural and Evolutionary Computing Spiking Neural Networks (SNNs) are highly energy-efficient due to event-driven, sparse computation, but their training is challenged by spike non-differentiability and trade-offs among performance, efficiency, and biological plausibility. Crucially, mainstream SNNs ignore predictive coding, a core cortical mechanism where the brain predicts inputs and encodes errors for efficient perception. Inspired by this, we propose a self-prediction enhanced spiking neuron method that generates an internal prediction current from its input-output history to modulate membrane potential. This design offers dual advantages, it creates a continuous gradient path that alleviates vanishing gradients and boosts training stability and accuracy, while also aligning with biological principles, which resembles distal dendritic modulation and error-driven synaptic plasticity. Experiments show consistent performance gains across diverse architectures, neuron types, time steps, and tasks demonstrating broad applicability for enhancing SNNs. |
| title | General Self-Prediction Enhancement for Spiking Neurons |
| topic | Neural and Evolutionary Computing |
| url | https://arxiv.org/abs/2601.21823 |