Scholarlink

This paper presents an Explainable AI (XAI) method for explaining Spiking Neural Networks (SNNs) through surrogate modeling. The proposed method involves translating trained SNNs into an equivalent Multi-Layer Perceptron (MLP) model, and enabling the use of standard post-hoc explanation techniques such as Shapley Additive Explanation (SHAP). The translation framework, implemented in Nengo, includes a custom weight-mapping and Leaky Integrate-and-Fire Rate (LIFRate)-based activation to approximate spiking behaviour. On a binary Distributed Denial-of-Service (DDoS) detection task, the translated model achieved lower accuracy (0.87) than benchmark MLPs (0.99–1.00), but identified the same key features. Further experiments showed that Recursive Least Squares (RLS)-trained SNNs consistently outperformed Prescribed Error-Sensitivity (PES)-trained variants.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Surrogate Models of Spiking Neural Networks for Explainability

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Jane Jung,
  • Matthew M. Y. Kuo,
  • Nathan Allen

摘要

This paper presents an Explainable AI (XAI) method for explaining Spiking Neural Networks (SNNs) through surrogate modeling. The proposed method involves translating trained SNNs into an equivalent Multi-Layer Perceptron (MLP) model, and enabling the use of standard post-hoc explanation techniques such as Shapley Additive Explanation (SHAP). The translation framework, implemented in Nengo, includes a custom weight-mapping and Leaky Integrate-and-Fire Rate (LIFRate)-based activation to approximate spiking behaviour. On a binary Distributed Denial-of-Service (DDoS) detection task, the translated model achieved lower accuracy (0.87) than benchmark MLPs (0.99–1.00), but identified the same key features. Further experiments showed that Recursive Least Squares (RLS)-trained SNNs consistently outperformed Prescribed Error-Sensitivity (PES)-trained variants.