Gradient-based feature-attribution explainability methods for spiking neural networks.

ABSTRACT:

Introduction

Spiking neural networks (SNNs) are a model of computation that mimics the behavior of biological neurons. SNNs process event data (spikes) and operate more sparsely than artificial neural networks (ANNs), resulting in ultra-low latency and small power consumption. This paper aims to adapt and evaluate gradient-based explainability methods for SNNs, which were originally developed for conventional ANNs.

Methods

The adapted methods aim to create input feature attribution maps for SNNs trained through backpropagation that process either event-based spiking data or real-valued data. The methods address the limitations of existing work on explainability methods for SNNs, such as poor scalability, limited to convolutional layers, requiring the training of another mode

SUBMITTER: Bitar A 

PROVIDER: S-EPMC10565802 | biostudies-literature | 2023

REPOSITORIES: biostudies-literature