用预训练网络生成脉冲信号，实现高性能类脑分类。
Hybrid ANN-SNN Pipeline with Local Plasticity
- 用速率编码将ANN激活转为脉冲，再用局部学习规则训练SNN
- 在ImageNet 64类上达到99.09%准确率，媲美传统深度网络
- 适合想高效部署类脑模型的研究者和工程师
本文提出一种混合ANN-SNN流水线，有效利用预训练人工神经网络（ANN）的丰富特征表示，实现高性能脉冲神经网络（SNN）。该架构将预训练的EfficientNet编码器与CoLaNET脉冲分类器结合，通过速率编码将编码器激活转换为脉冲序列，并采用局部、生物启发的学习规则训练后续SNN分类器，避免端到端梯度传播。该方法在64类ImageNet基准上达到99.09%准确率，性能与传统深度网络相当。本工作提供了一种生物合理且高效的框架，用于将强大预训练编码器适配至下游脉冲神经网络任务。
原文摘要 · Abstract (English)
This work proposes a hybrid ANN-SNN pipeline that effectively leverages the rich embeddings of pretrained artificial neural networks (ANNs) to enable high-performance spiking neural networks (SNNs). The architecture couples a pretrained EfficientNet encoder with a CoLaNET spiking classifier. We convert the encoder's activations into spike trains via rate-coding and train the subsequent SNN classifier using local, biologically inspired learning rules, bypassing end-to-end gradient propagation. This approach achieves 99.09% accuracy on a 64-class ImageNet benchmark, demonstrating performance on par with conventional deep networks. The work presents a biologically plausible and efficient framework for adapting powerful pretrained encoders to downstream spiking neural network tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。