A Scale-Invariant Diagnostic Approach Towards Understanding Dynamics of Deep Neural Networks
Neural and Evolutionary Computing
2024-07-16 v1 Artificial Intelligence
Abstract
This paper introduces a scale-invariant methodology employing \textit{Fractal Geometry} to analyze and explain the nonlinear dynamics of complex connectionist systems. By leveraging architectural self-similarity in Deep Neural Networks (DNNs), we quantify fractal dimensions and \textit{roughness} to deeply understand their dynamics and enhance the quality of \textit{intrinsic} explanations. Our approach integrates principles from Chaos Theory to improve visualizations of fractal evolution and utilizes a Graph-Based Neural Network for reconstructing network topology. This strategy aims at advancing the \textit{intrinsic} explainability of connectionist Artificial Intelligence (AI) systems.
Keywords
Cite
@article{arxiv.2407.09585,
title = {A Scale-Invariant Diagnostic Approach Towards Understanding Dynamics of Deep Neural Networks},
author = {Ambarish Moharil and Damian Tamburri and Indika Kumara and Willem-Jan Van Den Heuvel and Alireza Azarfar},
journal= {arXiv preprint arXiv:2407.09585},
year = {2024}
}