Binary Spiking Neural Networks as Causal Models

arXiv cs.AI / 5/1/2026

💬 OpinionIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper presents a causal analysis framework for Binary Spiking Neural Networks (BSNNs) by formalizing their spiking dynamics as a binary causal model.
It shows that, once framed causally, BSNN outputs can be explained using logic-based reasoning techniques, including SAT and SMT solvers for abductive explanations.
The authors train a BSNN on MNIST and use SAT/SMT methods to generate feature-level (pixel-level) abductive explanations of the network’s classifications.
The generated explanations are compared with SHAP, and the paper claims their method—unlike SHAP—can guarantee that explanations do not include completely irrelevant features.
Overall, the work connects spiking neural networks with causal modeling and formal verification-style solvers to improve interpretability guarantees.

Abstract

We provide a causal analysis of Binary Spiking Neural Networks (BSNNs) to explain their behavior. We formally define a BSNN and represent its spiking activity as a binary causal model. Thanks to this causal representation, we are able to explain the output of the network by leveraging logic-based methods. In particular, we show that we can successfully use a SAT as well as a SMT solver to compute abductive explanations from this binary causal model. To illustrate our approach, we trained the BSNN on the standard MNIST dataset and applied our SAT-based and SMT-based methods to finding abductive explanations of the network's classifications based on pixel-level features. We also compared the found explanations against SHAP, a popular method used in the area of explainable AI. We show that, unlike SHAP, our approach guarantees that a found explanation does not contain completely irrelevant features.