English

Front-propagation Algorithm: Explainable AI Technique for Extracting Linear Function Approximations from Neural Networks

Artificial Intelligence 2024-05-28 v1 Machine Learning

Abstract

This paper introduces the front-propagation algorithm, a novel eXplainable AI (XAI) technique designed to elucidate the decision-making logic of deep neural networks. Unlike other popular explainability algorithms such as Integrated Gradients or Shapley Values, the proposed algorithm is able to extract an accurate and consistent linear function explanation of the network in a single forward pass of the trained model. This nuance sets apart the time complexity of the front-propagation as it could be running real-time and in parallel with deployed models. We packaged this algorithm in a software called front-prop\texttt{front-prop} and we demonstrate its efficacy in providing accurate linear functions with three different neural network architectures trained on publicly available benchmark datasets.

Keywords

Cite

@article{arxiv.2405.16259,
  title  = {Front-propagation Algorithm: Explainable AI Technique for Extracting Linear Function Approximations from Neural Networks},
  author = {Javier Viaña},
  journal= {arXiv preprint arXiv:2405.16259},
  year   = {2024}
}

Comments

14 pages, 6 figures. Accepted for publication in: Barnabas Bede, Kelly Cohen, and Vladik Kreinovich (eds.), Proceedings of the NAFIPS International Conference on Fuzzy Systems, Soft Computing, and Explainable AI. NAFIPS'2024, South Padre Island, Texas, May 27-29, 2024

R2 v1 2026-06-28T16:40:17.111Z