all AI news
Front-propagation Algorithm: Explainable AI Technique for Extracting Linear Function Approximations from Neural Networks
May 28, 2024, 4:45 a.m. | Javier Via\~na
cs.LG updates on arXiv.org arxiv.org
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 …
abstract algorithm algorithms arxiv cs.ai cs.lg decision explainability explainable ai extract front function linear logic making networks neural networks novel paper popular propagation type values xai
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Senior Data Engineer
@ Displate | Warsaw
Senior Robotics Engineer - Applications
@ Vention | Montréal, QC, Canada
Senior Application Security Engineer, SHINE - Security Hub for Innovation and Efficiency
@ Amazon.com | Toronto, Ontario, CAN
Simulation Scientist , WWDE Simulation
@ Amazon.com | Bellevue, Washington, USA
Giáo Viên Steam
@ Việc Làm Giáo Dục | Da Nang, Da Nang, Vietnam
Senior Simulation Developer
@ Vention | Montréal, QC, Canada