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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Viaña, Javier
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913362875514880
author Viaña, Javier
author_facet Viaña, Javier
contents 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 $\texttt{front-prop}$ and we demonstrate its efficacy in providing accurate linear functions with three different neural network architectures trained on publicly available benchmark datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2405_16259
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Front-propagation Algorithm: Explainable AI Technique for Extracting Linear Function Approximations from Neural Networks
Viaña, Javier
Artificial Intelligence
Machine Learning
68T07
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 $\texttt{front-prop}$ and we demonstrate its efficacy in providing accurate linear functions with three different neural network architectures trained on publicly available benchmark datasets.
title Front-propagation Algorithm: Explainable AI Technique for Extracting Linear Function Approximations from Neural Networks
topic Artificial Intelligence
Machine Learning
68T07
url https://arxiv.org/abs/2405.16259