AI RESEARCH
From Weight Perturbation to Feature Attribution for Explaining Fully Connected Neural Networks
arXiv CS.LG
•
ArXi:2605.15328v1 Announce Type: new Fully Connected Neural Networks (FCNNs) are often regarded as simple and intuitive architectures, yet they serve as the foundation for complex models. Nonetheless, the lack of consensus on their interpretability continues to pose challenges, underscoring the enduring relevance of simpler, attribution-based approaches for understanding even the most advanced neural architectures. In this regard, we explore a novel idea for estimating feature attribution, by applying perturbation to the features' attached weights instead of their values.