Hybrid Layer-Wise ANN-SNN With Surrogate Spike Encoding-Decoding Structure
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909814513205248 |
|---|---|
| author | Luu, Nhan T. Luu, Duong T. Nam, Pham Ngoc Thang, Truong Cong |
| author_facet | Luu, Nhan T. Luu, Duong T. Nam, Pham Ngoc Thang, Truong Cong |
| contents | Spiking Neural Networks (SNNs) have gained significant traction in both computational neuroscience and artificial intelligence for their potential in energy-efficient computing. In contrast, artificial neural networks (ANNs) excel at gradient-based optimization and high accuracy. This contrast has consequently led to a growing subfield of hybrid ANN-SNN research. However, existing hybrid approaches often rely on either a strict separation between ANN and SNN components or employ SNN-only encoders followed by ANN classifiers due to the constraints of non-differentiability of spike encoding functions, causing prior hybrid architectures to lack deep layer-wise cooperation during backpropagation. To address this gap, we propose a novel hybrid ANN-SNN framework that integrates layer-wise encode-decode SNN blocks within conventional ANN pipelines. Central to our method is the use of surrogate gradients for a bit-plane-based spike encoding function, enabling end-to-end differentiable training across ANN and SNN layers. This design achieves competitive accuracy with state-of-the-art pure ANN and SNN models while retaining the potential efficiency and temporal representation benefits of spiking computation. To the best of our knowledge, this is the first implementation of a surrogate gradient for bit plane coding specifically and spike encoder interface in general to be utilized in the context of hybrid ANN-SNN, successfully leading to a new class of hybrid models that pave new directions for future research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_24411 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Hybrid Layer-Wise ANN-SNN With Surrogate Spike Encoding-Decoding Structure Luu, Nhan T. Luu, Duong T. Nam, Pham Ngoc Thang, Truong Cong Neural and Evolutionary Computing Artificial Intelligence Computer Vision and Pattern Recognition Spiking Neural Networks (SNNs) have gained significant traction in both computational neuroscience and artificial intelligence for their potential in energy-efficient computing. In contrast, artificial neural networks (ANNs) excel at gradient-based optimization and high accuracy. This contrast has consequently led to a growing subfield of hybrid ANN-SNN research. However, existing hybrid approaches often rely on either a strict separation between ANN and SNN components or employ SNN-only encoders followed by ANN classifiers due to the constraints of non-differentiability of spike encoding functions, causing prior hybrid architectures to lack deep layer-wise cooperation during backpropagation. To address this gap, we propose a novel hybrid ANN-SNN framework that integrates layer-wise encode-decode SNN blocks within conventional ANN pipelines. Central to our method is the use of surrogate gradients for a bit-plane-based spike encoding function, enabling end-to-end differentiable training across ANN and SNN layers. This design achieves competitive accuracy with state-of-the-art pure ANN and SNN models while retaining the potential efficiency and temporal representation benefits of spiking computation. To the best of our knowledge, this is the first implementation of a surrogate gradient for bit plane coding specifically and spike encoder interface in general to be utilized in the context of hybrid ANN-SNN, successfully leading to a new class of hybrid models that pave new directions for future research. |
| title | Hybrid Layer-Wise ANN-SNN With Surrogate Spike Encoding-Decoding Structure |
| topic | Neural and Evolutionary Computing Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.24411 |