Direct-to-Event Spiking Neural Network Transfer
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915991594729472 |
|---|---|
| author | Luu, Nhan Trong Luu, Duong Trung Nam, Pham Ngoc Thang, Truong Cong |
| author_facet | Luu, Nhan Trong Luu, Duong Trung Nam, Pham Ngoc Thang, Truong Cong |
| contents | Spiking Neural Networks (SNNs) have gained increasing attention due to their potential for low-power computation on neuromorphic hardware. A widely adopted training strategy for SNNs is direct coding, which enable backpropagation on neuron implementations using continuous-valued surrogate activations. However, recent studies have shown that direct-coded SNNs remain substantially less energy-efficient than their event-based counterparts, limiting their practical deployment in energy sensitive scenarios. Still, to promote the reusability of pretrained SNN database on direct code, this motivates an important yet underexplored question: How can a SNN pretrained with direct code be effectively converted into an event-based representation? In this research, we present the first systematic investigation into this transfer problem, analyze the key challenges that arise when transitioning from direct-coded to event-based computation and propose a set of methods to enable energy-efficient transfer while preserving model performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_07207 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Direct-to-Event Spiking Neural Network Transfer Luu, Nhan Trong Luu, Duong Trung Nam, Pham Ngoc Thang, Truong Cong Neural and Evolutionary Computing Spiking Neural Networks (SNNs) have gained increasing attention due to their potential for low-power computation on neuromorphic hardware. A widely adopted training strategy for SNNs is direct coding, which enable backpropagation on neuron implementations using continuous-valued surrogate activations. However, recent studies have shown that direct-coded SNNs remain substantially less energy-efficient than their event-based counterparts, limiting their practical deployment in energy sensitive scenarios. Still, to promote the reusability of pretrained SNN database on direct code, this motivates an important yet underexplored question: How can a SNN pretrained with direct code be effectively converted into an event-based representation? In this research, we present the first systematic investigation into this transfer problem, analyze the key challenges that arise when transitioning from direct-coded to event-based computation and propose a set of methods to enable energy-efficient transfer while preserving model performance. |
| title | Direct-to-Event Spiking Neural Network Transfer |
| topic | Neural and Evolutionary Computing |
| url | https://arxiv.org/abs/2605.07207 |