{"ID":2863390,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.24411","arxiv_id":"2509.24411","title":"Hybrid Layer-Wise ANN-SNN With Surrogate Spike Encoding-Decoding Structure","abstract":"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.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2509.24411","url_pdf":"https://arxiv.org/pdf/2509.24411v1","authors":"[\"Nhan T. Luu\",\"Duong T. Luu\",\"Pham Ngoc Nam\",\"Truong Cong Thang\"]","published":"2025-09-29T07:57:58Z","proceeding":"cs.NE","tasks":"[\"cs.NE\",\"cs.AI\",\"cs.CV\"]","methods":"[]","has_code":false}