A Scale-Invariant Diagnostic Approach Towards Understanding Dynamics of Deep Neural Networks
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913430073507840 |
|---|---|
| author | Moharil, Ambarish Tamburri, Damian Kumara, Indika Heuvel, Willem-Jan Van Den Azarfar, Alireza |
| author_facet | Moharil, Ambarish Tamburri, Damian Kumara, Indika Heuvel, Willem-Jan Van Den Azarfar, Alireza |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_09585 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Scale-Invariant Diagnostic Approach Towards Understanding Dynamics of Deep Neural Networks Moharil, Ambarish Tamburri, Damian Kumara, Indika Heuvel, Willem-Jan Van Den Azarfar, Alireza Neural and Evolutionary Computing Artificial Intelligence 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. |
| title | A Scale-Invariant Diagnostic Approach Towards Understanding Dynamics of Deep Neural Networks |
| topic | Neural and Evolutionary Computing Artificial Intelligence |
| url | https://arxiv.org/abs/2407.09585 |