Binary Spiking Neural Networks as causal models
Keywords: Explainability, Causal reasoning, Spiking Neural Networks, White-box
Abstract: In this paper, we provide a causal analysis of binary spiking neural networks (BSNNs)
aimed at explaining their behaviors.
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 (Boolean satisfiability) 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 method 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 to explain ``black box'' classifiers.
We show that, unlike SHAP,
our method guarantees that a found explanation does
not contain completely irrelevant features.
Supplementary Material: zip
Primary Area: causal reasoning
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 14144
Loading